© 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. 69599
    Prev
    Next
    INDEX
    Explanations

    summer wedding bike show

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

    biofilms around

    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
    ｻ
    0.50
     vingt
    0.49
     putty
    0.47
     samud
    0.46
     loko
    0.45
    とその
    0.45
    𝖠
    0.43
     gacch
    0.42
     katva
    0.42
    っていない
    0.42
    POSITIVE LOGITS
     #
    0.52
    new
    0.46
     memorial
    0.45
     Memorial
    0.44
    调整
    0.44
    hs
    0.44
    ims
    0.44
    liest
    0.43
    auto
    0.43
     $\
    0.42
    Activations Density 0.001%

    No Known Activations