© 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. 126700
    Prev
    Next
    INDEX
    Explanations

    mild risk flute clone you

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

    food order

    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
    テム
    0.50
    ים
    0.48
    ﻔ
    0.47
     depositphotos
    0.47
    ubles
    0.46
    clientsdetails
    0.45
     investors
    0.45
    ed
    0.44
    ترام
    0.44
    Caribbean
    0.43
    POSITIVE LOGITS
     ступен
    0.55
     ಮಾಡುವ
    0.51
    avik
    0.46
     있었다
    0.44
     править
    0.44
     있었
    0.43
    acketing
    0.43
    梩
    0.43
    anesha
    0.42
     enregistré
    0.42
    Activations Density 0.000%

    No Known Activations