© 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. 107694
    Prev
    Next
    INDEX
    Explanations

    indicator names setting Samba

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

    hands intertwined

    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
     sentimento
    0.48
    జేపీ
    0.45
    隧道
    0.45
     tumor
    0.45
     antitumor
    0.44
    僵
    0.44
     xī
    0.43
    ඩ
    0.43
    と思って
    0.42
    🦁
    0.42
    POSITIVE LOGITS
    all
    0.61
    an
    0.58
    line
    0.54
    atgu
    0.54
    al
    0.52
    as
    0.52
    is
    0.51
    etragen
    0.50
    ueba
    0.50
    register
    0.49
    Activations Density 0.000%

    No Known Activations