© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 9585
    Prev
    Next
    INDEX
    Explanations

    a b c list items

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

    list item markers (2. or II.)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     například
    0.38
     lớ
    0.38
     例如
    0.33
     beispielsweise
    0.33
    
    0.33
     например
    0.32
     عام
    0.31
    АН
    0.31
    例如
    0.31
     práv
    0.31
    POSITIVE LOGITS
    k
    0.36
    )
    0.36
    ed
    0.36
    xious
    0.35
     Novos
    0.35
     Neces
    0.34
    b
    0.33
     mogu
    0.33
    ️⃣
    0.33
     Dist
    0.32
    Activations Density 0.036%

    No Known Activations