© 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. 128195
    Prev
    Next
    INDEX
    Explanations

    automatically collected or created

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

    autocommits or however

    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
     épais
    0.51
    য়েল
    0.50
    ленні
    0.47
    辏
    0.45
    entlich
    0.45
     discontinuation
    0.44
    лом
    0.43
    ่วย
    0.43
    кли
    0.43
     отлично
    0.42
    POSITIVE LOGITS
    d
    0.56
    t
    0.52
    in
    0.51
     Kola
    0.50
     ,
    0.49
     |
    0.48
     from
    0.48
    created
    0.48
    CREATED
    0.47
     in
    0.47
    Activations Density 0.000%

    No Known Activations