© 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. 52737
    Prev
    Next
    INDEX
    Explanations

    from or vendors any example invisible block and rejected today

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

    just want to chat

    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
    ד
    0.54
     OIL
    0.51
     Señor
    0.50
     potenz
    0.47
     amt
    0.47
     Président
    0.47
     fratello
    0.46
     Oil
    0.46
    ي
    0.46
     druge
    0.46
    POSITIVE LOGITS
    UserDetails
    0.49
    Employ
    0.48
    CheckingType
    0.48
    队
    0.47
    йон
    0.45
    TransactionLog
    0.45
    inputType
    0.44
    Mutation
    0.43
     बीमा
    0.42
    Боль
    0.42
    Activations Density 0.000%

    No Known Activations