© 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. 20140
    Prev
    Next
    INDEX
    Explanations

    bill, finger, thing, these, study, 4, great, more

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

    briefly mention content structure

    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
     あり
    0.56
    ﾞ
    0.48
    Α
    0.48
     жизнен
    0.48
    ס
    0.48
     ת
    0.47
     گیا
    0.45
    がございます
    0.45
    ala
    0.45
    ゛
    0.45
    POSITIVE LOGITS
     Markers
    0.45
     నాలు
    0.44
     mustn
    0.44
     ఇంత
    0.43
     centimetres
    0.43
    cPix
    0.42
     statutes
    0.40
     Consecutive
    0.40
    LENGTH
    0.40
     ছুটি
    0.40
    Activations Density 0.000%

    No Known Activations