© 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. 35945
    Prev
    Next
    INDEX
    Explanations

    Board discussion

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

    OBDII code, Lobster Rolls

    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
    玳
    0.49
    红色
    0.46
    宁波
    0.46
    摭
    0.45
    木
    0.44
    껀
    0.43
     ello
    0.43
    阴
    0.43
    吲
    0.43
    苍
    0.43
    POSITIVE LOGITS
    girls
    0.46
    нечно
    0.45
    िश्च
    0.44
    μένη
    0.44
    میان
    0.44
    oucester
    0.44
     concurrence
    0.44
     Parigi
    0.44
    cées
    0.44
    ‚¬
    0.43
    Activations Density 0.000%

    No Known Activations