© 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. 158815
    Prev
    Next
    INDEX
    Explanations

    explains; have; voters; respond; family; fonts; take

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

    list items, points, or actions

    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
    (\|\
    0.47
     rehearsals
    0.45
     периода
    0.43
     построе
    0.43
    (|\
    0.43
     الماضي
    0.42
    η
    0.42
    後期
    0.42
     народа
    0.42
     nomads
    0.41
    POSITIVE LOGITS
    ylsulfanyl
    0.53
    sadpoetry
    0.51
    oL
    0.49
    दित
    0.48
    বরা
    0.48
    ต
    0.48
     انکار
    0.48
     retort
    0.48
    聝
    0.47
    riti
    0.47
    Activations Density 0.001%

    No Known Activations