© 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. 79414
    Prev
    Next
    INDEX
    Explanations

    Deloitte, automobile, Delphi, HP

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

    MUI, costs, want

    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
    -
    0.53
    ()
    0.46
    ,
    0.46
    (
    0.42
     algorithm
    0.41
    2
    0.40
     Dublin
    0.39
    roman
    0.39
     ireland
    0.39
    CBS
    0.38
    POSITIVE LOGITS
     ರೈ
    0.50
     хотим
    0.49
     ಆತ್ಮ
    0.49
     ಮಿಶ್ರ
    0.49
     приятно
    0.49
     इकट्ठा
    0.47
     தயார
    0.47
     uitgen
    0.46
    <unused39>
    0.46
     vogliamo
    0.46
    Activations Density 0.002%

    No Known Activations