© 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. 87818
    Prev
    Next
    INDEX
    Explanations

    update and information

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

    style descriptors

    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
     legato
    0.49
     produzione
    0.45
     problemen
    0.44
    زالة
    0.44
    ട്ടി
    0.43
    求解
    0.43
    Workflow
    0.43
    栱
    0.43
    堌
    0.42
    <unused67>
    0.42
    POSITIVE LOGITS
    non
    0.46
    परि
    0.45
    television
    0.44
    soft
    0.44
    not
    0.42
     beliau
    0.42
    ays
    0.42
    consc
    0.41
    ate
    0.40
    ne
    0.40
    Activations Density 0.004%

    No Known Activations