© 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. 616
    Prev
    Next
    INDEX
    Explanations

    local context and associations

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

    local specific contexts

    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
     weltweit
    0.48
     Conde
    0.45
     düş
    0.43
     ovog
    0.42
     enfer
    0.41
     Angew
    0.41
     Toán
    0.40
     "=",
    0.40
     Protok
    0.40
     Međ
    0.40
    POSITIVE LOGITS
    local
    1.63
     local
    1.53
     स्थानीय
    1.47
    本地
    1.46
    Local
    1.44
    LOCAL
    1.44
     लोकल
    1.38
     lokal
    1.37
     местные
    1.36
     LOCAL
    1.34
    Activations Density 0.247%

    No Known Activations