© 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. 208345
    Prev
    Next
    INDEX
    Explanations

    seek advice and notify

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

    reporting calculations simple

    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
    不良
    0.55
     militaires
    0.48
    ᱑
    0.46
     Okan
    0.46
    スーツ
    0.46
    가가
    0.46
     नीरज
    0.46
    郤
    0.45
    ilitar
    0.44
    ێکی
    0.44
    POSITIVE LOGITS
     Seat
    0.47
     whole
    0.46
     seat
    0.46
    ing
    0.46
     on
    0.44
     notify
    0.42
     learner
    0.42
     gnome
    0.42
     consult
    0.42
     summons
    0.41
    Activations Density 0.000%

    No Known Activations