© 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. 80591
    Prev
    Next
    INDEX
    Explanations

    end of process or sentence

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

    functionality or specific context

    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
    インド
    0.56
    u
    0.53
    ק
    0.50
    uene
    0.49
    aruhi
    0.47
    ੧
    0.45
    financed
    0.45
    uig
    0.44
    ะ
    0.44
    cities
    0.44
    POSITIVE LOGITS
     Witch
    0.52
     Ske
    0.47
     Maybe
    0.46
     Sock
    0.46
     حسب
    0.45
     Sanit
    0.45
     Tackle
    0.45
     tcpHeader
    0.44
     Characteristics
    0.44
     Missile
    0.44
    Activations Density 0.001%

    No Known Activations