© 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. 64839
    Prev
    Next
    INDEX
    Explanations

    ai, Car, Lai, Lit, Sto, stiff, Lizard, Brussels

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

    edge strategy

    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
     cardí
    0.49
    성의
    0.47
    猶
    0.47
    竅
    0.45
    ከላ
    0.45
     leger
    0.44
    성은
    0.44
    성이
    0.43
    פס
    0.43
    性の
    0.43
    POSITIVE LOGITS
    ai
    0.46
     Car
    0.45
     Lai
    0.44
     Lit
    0.44
     Sto
    0.42
     stiff
    0.41
     Lizard
    0.41
     Brussels
    0.41
     L
    0.41
     Editors
    0.41
    Activations Density 0.000%

    No Known Activations