© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 147681
    Prev
    Next
    INDEX
    Explanations

    project planning, job duties

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

    definitions and technical terms

    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
     Headache
    0.45
     prachtige
    0.44
     coronavirus
    0.43
     Nevada
    0.43
    >
    0.43
     pounds
    0.42
     Corona
    0.42
     ремонт
    0.42
     deterior
    0.42
     समस्याओं
    0.41
    POSITIVE LOGITS
    grant
    0.52
    ენტის
    0.51
    రు
    0.49
    ክል
    0.48
    􀂃
    0.46
     conferring
    0.46
     enforceable
    0.45
    ოში
    0.45
    ટક
    0.45
    ించాలని
    0.44
    Activations Density 0.002%

    No Known Activations