© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108897
    Prev
    Next
    INDEX
    Explanations

    degeneration, degradation, deform, degrease

    np_acts-logits-general · gemini-2.5-flash-lite

    words starting with "degra" or "degre" related to degradation or breaking down.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires strongly on occurrences of the “degr‐” root (e.g. degradation, degradative, degradable, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     conoscere
    -1.00
    betical
    -0.97
     desperately
    -0.96
     dammit
    -0.94
     redaktion
    -0.93
    ȏ
    -0.93
     pfle
    -0.90
    .,"
    -0.87
     inizia
    -0.87
     periodical
    -0.87
    POSITIVE LOGITS
     De
    1.71
    De
    1.67
     Де
    1.03
     デ
    0.98
    having
    0.91
     Dee
    0.88
    éis
    0.85
     Deg
    0.83
    fährt
    0.82
    drm
    0.80
    Activations Density 0.049%

    No Known Activations