© 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. 243830
    Prev
    Next
    INDEX
    Explanations

    listing nouns or actions

    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
     himself
    0.44
     ll
    0.43
    l
    0.42
     Mishra
    0.42
     allClasses
    0.42
     Binary
    0.42
    omores
    0.42
    iejs
    0.41
    ကြောင်း
    0.40
     između
    0.40
    POSITIVE LOGITS
     diduga
    0.49
    vasion
    0.49
    weichen
    0.45
    диа
    0.45
    bagian
    0.45
     проек
    0.45
    %、
    0.45
    жают
    0.45
    вин
    0.44
     ото
    0.44
    Activations Density 0.000%

    No Known Activations