© 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. 109707
    Prev
    Next
    INDEX
    Explanations

    not affiliated with

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

    located or number

    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
    مو
    0.52
    тинен
    0.50
    鳞
    0.50
    プーン
    0.48
     частини
    0.47
    仕事
    0.46
     determines
    0.44
    槇
    0.44
    স্থানের
    0.44
     হইয়৷
    0.44
    POSITIVE LOGITS
    lege
    0.44
    silent
    0.43
     balón
    0.43
    impose
    0.43
    flat
    0.42
    ván
    0.42
    quel
    0.42
    fé
    0.41
     triangular
    0.41
     ruhig
    0.41
    Activations Density 0.000%

    No Known Activations