© 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. 121042
    Prev
    Next
    INDEX
    Explanations

    official releases, servers, lakefronts, new laws

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

    relationship jokes, business jargon, smart features

    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
     graced
    0.47
    ah
    0.46
    Ọ
    0.43
     buz
    0.43
    ispo
    0.43
    дут
    0.42
     muze
    0.42
    ాప
    0.42
    inic
    0.41
    engined
    0.41
    POSITIVE LOGITS
     Translation
    0.55
     Interpretation
    0.52
     India
    0.51
    ):
    0.50
     Alternative
    0.50
     SE
    0.50
     yearbook
    0.49
     BASIC
    0.48
     portfolio
    0.48
     Portfolio
    0.48
    Activations Density 0.000%

    No Known Activations