© 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. 197774
    Prev
    Next
    INDEX
    Explanations

    family missions

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

    simple audio text explain

    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
    izzes
    0.46
    cav
    0.46
    cobra
    0.46
    I
    0.46
     Coast
    0.45
    __(/*!
    0.45
     да
    0.44
    ків
    0.44
    да
    0.44
    ть
    0.44
    POSITIVE LOGITS
    modelo
    0.56
    resultado
    0.50
    亠
    0.47
    لاقي
    0.46
    נטי
    0.45
    Parte
    0.44
     विचारक
    0.43
    Modelo
    0.43
     casado
    0.42
    وني
    0.42
    Activations Density 0.001%

    No Known Activations