© 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. 218938
    Prev
    Next
    INDEX
    Explanations

    indicating that

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

    short & pronounceable

    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
    ெல்லி
    0.51
    Ⲑ
    0.49
    の場合は
    0.46
    ⚤
    0.44
    fromi
    0.44
    ṑ
    0.43
    hiyam
    0.43
    ErrMsg
    0.43
     trotzdem
    0.43
     dennoch
    0.42
    POSITIVE LOGITS
    job
    0.50
    RUB
    0.49
     job
    0.47
    breve
    0.46
    OT
    0.46
    rub
    0.46
    2
    0.45
    IDs
    0.44
    Y
    0.44
    sticky
    0.43
    Activations Density 0.003%

    No Known Activations