© 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. 72481
    Prev
    Next
    INDEX
    Explanations

    or depending on

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     núm
    -1.13
     ficou
    -1.11
     pani
    -1.11
    ABILITY
    -1.11
     kato
    -1.07
     vó
    -1.06
     nij
    -1.05
     börja
    -1.05
     ומ
    -1.04
     ngan
    -1.04
    POSITIVE LOGITS
     or
    2.53
     if
    1.92
     depending
    1.79
     be
    1.69
    也可以
    1.61
     Depending
    1.59
    Depending
    1.52
    Many
    1.42
     may
    1.39
     many
    1.39
    Activations Density 0.119%

    No Known Activations