© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 72919
    Prev
    Next
    INDEX
    Explanations

    field or removal

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

    The neuron fires on content-bearing or otherwise uncommon tokens—i.e. rarer, technical words and punctuation (like “algorithms,” “discrete,” “that,” “use,” “:”) that carry high informational weight in the document.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     prévention
    -1.02
     substan
    -1.01
     Dinas
    -0.97
    Olvid
    -0.96
     réellement
    -0.94
    畠
    -0.93
    苼
    -0.90
    eniem
    -0.89
     Để
    -0.88
    șa
    -0.88
    POSITIVE LOGITS
     all
    1.16
     और
    1.06
     funds
    0.91
     pemilihan
    0.91
     và
    0.85
     dostęp
    0.84
     begleitet
    0.82
     current
    0.82
     mostly
    0.82
     anuales
    0.81
    Activations Density 0.039%

    No Known Activations