© 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. 22-GEMMASCOPE-RES-131K
    7. 66272
    Prev
    Next
    INDEX
    Explanations

    difference or similarity

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

    The neuron fires on discourse‐linking cue words (like because, when, thus, often, that, each) that introduce explanations, cause‐and‐effect, or elaboration in technical text.

    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
     anderen
    -1.00
     passend
    -0.97
     sonidos
    -0.94
     estrés
    -0.90
     another
    -0.90
     questo
    -0.88
    jandro
    -0.85
     a
    -0.85
     likewise
    -0.84
    iest
    -0.80
    POSITIVE LOGITS
     latter
    1.92
    后者
    1.64
    latter
    1.35
     keduanya
    1.34
    Both
    1.23
     difference
    1.23
    Unlike
    1.10
     nikah
    1.03
    While
    1.02
    difference
    0.99
    Activations Density 0.058%

    No Known Activations