© 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. 54153
    Prev
    Next
    INDEX
    Explanations

    educational opportunities

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

    factual details and specific conditions

    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
     is
    0.59
    </strong>
    0.55
     was
    0.54
     to
    0.53
     would
    0.52
    è
    0.49
     says
    0.49
    ë
    0.48
     It
    0.47
     that
    0.47
    POSITIVE LOGITS
    ेंगू
    0.51
    मनी
    0.50
    PART
    0.49
    StoredKeys
    0.48
    ANDE
    0.47
     disponer
    0.47
    धे
    0.47
    θηκαν
    0.47
    ISION
    0.47
    ЕНИЕ
    0.46
    Activations Density 0.000%

    No Known Activations