© 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. 54660
    Prev
    Next
    INDEX
    Explanations

    news and facts

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

    time until words

    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
     satellite
    0.45
    ض
    0.44
     consultant
    0.42
    權
    0.42
    ন্দর
    0.41
     shield
    0.40
     be
    0.40
     terrain
    0.39
    社区
    0.39
     trải
    0.39
    POSITIVE LOGITS
    anya
    0.50
    <unused260>
    0.49
    anin
    0.48
     auxqu
    0.47
     kelet
    0.47
     Langkah
    0.47
     अरविंद
    0.46
     berhenti
    0.46
     வண்ணம்
    0.46
     ఎమ్మె
    0.46
    Activations Density 0.000%

    No Known Activations