© 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. 88111
    Prev
    Next
    INDEX
    Explanations

    station and God night convert opens break

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

    specifying qualifiers

    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
     Freeze
    0.46
    теря
    0.45
    用於
    0.45
    و
    0.45
    罕
    0.45
    qm
    0.43
    取得
    0.43
    يده
    0.43
    as
    0.43
    시장
    0.42
    POSITIVE LOGITS
     เงิน
    0.48
     تجهیز
    0.46
     nawet
    0.46
     ]]
    0.44
     さらに
    0.43
     จริง
    0.43
     mitig
    0.43
    ിവ
    0.43
     renaming
    0.43
     whe
    0.42
    Activations Density 0.002%

    No Known Activations