© 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. 210739
    Prev
    Next
    INDEX
    Explanations

    labelling jams or IT projects

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

    translation and code instructions

    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
    梯
    0.43
     चक्कर
    0.43
    ሉም
    0.43
     remnants
    0.42
    械
    0.42
    思路
    0.42
    Scrim
    0.41
    ണ്ട
    0.40
    follows
    0.40
    kanal
    0.39
    POSITIVE LOGITS
    ала
    0.45
    贻
    0.45
     suj
    0.43
    見える
    0.42
     ці
    0.42
     расти
    0.42
     vaš
    0.41
    IST
    0.41
     מח
    0.41
     ваши
    0.41
    Activations Density 0.000%

    No Known Activations