© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 61539
    Prev
    Next
    INDEX
    Explanations

    Mr. names, Net Margin, old town

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

    Tiger Capabilities, Boo's protection, navigation options

    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
     ಅಥವಾ
    0.51
    堷
    0.50
    밂
    0.49
     அல்லது
    0.47
     límites
    0.46
     లేదా
    0.46
     seguimiento
    0.46
     उपेंद्र
    0.46
    adres
    0.46
     utilizando
    0.45
    POSITIVE LOGITS
     moiety
    0.48
    うち
    0.45
    द
    0.44
     thanks
    0.44
     privilege
    0.44
    nY
    0.44
    #
    0.44
     \
    0.43
    ล
    0.43
    NY
    0.43
    Activations Density 0.000%

    No Known Activations