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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 36430
    Prev
    Next
    INDEX
    Explanations

    journal volume numbers

    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
     should
    -1.25
    เคย
    -1.21
     when
    -1.13
     if
    -1.11
     seem
    -1.03
    OrEqual
    -1.02
     seemed
    -1.01
    if
    -1.00
     seems
    -0.98
    onego
    -0.97
    POSITIVE LOGITS
     význam
    1.14
    をクリック
    1.13
    organisme
    1.07
    ďaka
    1.03
     INCREASE
    1.02
    ほんと
    1.02
    licante
    1.01
    ものに
    1.00
     Trouvez
    1.00
     extrêmement
    0.99
    Activations Density 0.003%

    No Known Activations