© 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. 104240
    Prev
    Next
    INDEX
    Explanations

    who spent

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

    events after that point

    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
    এল
    0.53
     Ellsworth
    0.49
     ofte
    0.47
     Helms
    0.46
    <unused35>
    0.46
    annis
    0.46
     dr
    0.46
     Tart
    0.46
     यूएस
    0.46
     roli
    0.46
    POSITIVE LOGITS
    你
    0.49
    ucional
    0.45
     arreglo
    0.44
    quanto
    0.44
    心
    0.43
    →
    0.42
    ↵
    0.42
    全力
    0.41
     descuento
    0.41
    vstack
    0.41
    Activations Density 0.000%

    No Known Activations