© 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. 68251
    Prev
    Next
    INDEX
    Explanations

    code documentation comments

    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
    nový
    -1.08
    println
    -1.06
     $
    -1.02
    osing
    -1.01
    on
    -0.99
     At
    -0.98
     The
    -0.96
    л
    -0.96
    MO
    -0.96
     on
    -0.96
    POSITIVE LOGITS
    Namen
    1.18
    帰って
    1.14
    背后
    1.11
    躓
    1.11
    Konto
    1.05
    Legende
    1.05
    凄く
    1.05
    Volumen
    1.05
    将他
    1.03
    Objekt
    1.02
    Activations Density 0.005%

    No Known Activations