© 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. 39473
    Prev
    Next
    INDEX
    Explanations

    potentially targeting

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

    technical language, rules, and specific concepts

    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
     እስከ
    0.46
    തു
    0.46
    国
    0.46
    רו
    0.44
     Расійскай
    0.44
    erie
    0.44
    чну
    0.43
    isle
    0.42
    <0xE7>
    0.42
     मित
    0.42
    POSITIVE LOGITS
     memcpy
    0.49
     endpoints
    0.46
     delimiters
    0.46
     logits
    0.45
     vertex
    0.44
     epitope
    0.44
     classifiers
    0.44
     modulus
    0.44
     annotation
    0.44
     xylem
    0.43
    Activations Density 0.000%

    No Known Activations