© 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. 28053
    Prev
    Next
    INDEX
    Explanations

    gift ideas and kitchen

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

    controls the center

    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
    in
    0.49
     성장
    0.49
    CEO
    0.47
    a
    0.46
     Harmonic
    0.45
    Atlantic
    0.45
     Atlantic
    0.44
     Germain
    0.44
    atine
    0.44
     Hals
    0.43
    POSITIVE LOGITS
     candidates
    0.49
     полити
    0.46
     collects
    0.46
     ଆ
    0.45
     politiques
    0.45
     differentiates
    0.44
     interess
    0.43
     observes
    0.43
     aspirants
    0.43
     routes
    0.43
    Activations Density 0.000%

    No Known Activations