© 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. 162383
    Prev
    Next
    INDEX
    Explanations

    County campaigning

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

    data analysis leads to changes

    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
    挤
    0.49
    லைன்
    0.48
     echi
    0.45
    ﾓ
    0.45
    theory
    0.44
    teams
    0.44
    ंज
    0.44
    濡
    0.44
    ﾏ
    0.44
    𝗲
    0.43
    POSITIVE LOGITS
    Peripheral
    0.45
     втор
    0.44
     pieces
    0.42
    pieces
    0.42
     compreender
    0.41
    usalem
    0.40
     لله
    0.40
     الدولة
    0.39
     ট্যা
    0.39
    Pieces
    0.39
    Activations Density 0.001%

    No Known Activations