© 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. 222516
    Prev
    Next
    INDEX
    Explanations

    locations and specific terms

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

    specific nouns followed by punctuation or common words

    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
    \*
    0.51
    ווה
    0.51
    Tính
    0.49
    *-
    0.48
    Come
    0.47
     Trock
    0.47
    SUR
    0.46
    ল
    0.46
     Come
    0.45
    Punj
    0.45
    POSITIVE LOGITS
     unjustly
    0.47
     ँ
    0.46
    петров
    0.46
     ابر
    0.45
    kag
    0.44
    inputSet
    0.43
    詳細は
    0.43
    帝国
    0.42
     lauren
    0.42
     Букмекеры
    0.42
    Activations Density 0.000%

    No Known Activations