© 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. 228987
    Prev
    Next
    INDEX
    Explanations

    Intent JS

    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
    يدات
    0.56
    炰
    0.54
     décisions
    0.53
    బా
    0.52
     concernant
    0.52
    谎
    0.50
    および
    0.50
    უბ
    0.49
    沤
    0.49
     reconnaître
    0.49
    POSITIVE LOGITS
     wheel
    0.55
    cycl
    0.53
    ce
    0.52
    co
    0.51
    ca
    0.50
     Indigenous
    0.49
    ed
    0.49
    ler
    0.48
    ED
    0.47
    yah
    0.47
    Activations Density 0.001%

    No Known Activations