© 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. 22848
    Prev
    Next
    INDEX
    Explanations

    shooting or gunfire

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

    setting up equations for variables

    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
    ষ্কার
    0.43
     нашли
    0.43
    clusión
    0.41
    呕
    0.41
    Variant
    0.41
    rée
    0.41
    仑
    0.40
    Anything
    0.40
     noyau
    0.39
    িনীর
    0.39
    POSITIVE LOGITS
     INTEGER
    0.45
     x
    0.44
    expressions
    0.41
     medical
    0.40
     memorial
    0.40
     Expressions
    0.40
     cost
    0.39
     Integer
    0.39
     express
    0.39
    7
    0.39
    Activations Density 0.002%

    No Known Activations