© 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. 86515
    Prev
    Next
    INDEX
    Explanations

    foreign words and phrases

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

    building structures or components

    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
     tine
    0.47
    만한
    0.44
     Últ
    0.43
    폭
    0.43
    一些
    0.42
    投注
    0.42
     μεγ
    0.41
     ہوئی
    0.41
     filmmaking
    0.41
    এ
    0.41
    POSITIVE LOGITS
    ry
    0.48
     appartiennent
    0.46
     forbids
    0.42
     dwellers
    0.41
     tohoto
    0.41
     ਨਹੀਂ
    0.41
     forcibly
    0.40
     inwoners
    0.40
     ankles
    0.40
    VECTOR
    0.40
    Activations Density 0.000%

    No Known Activations