© 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. 69191
    Prev
    Next
    INDEX
    Explanations

    managing expectations or situations

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

    language variations and control flow

    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
    sq
    0.46
    ?
    0.44
    ov
    0.43
    crop
    0.43
    ग
    0.42
    ujeme
    0.42
    ।
    0.41
    \(
    0.41
    xy
    0.41
    qv
    0.41
    POSITIVE LOGITS
     privé
    0.50
     нрави
    0.48
     sprawy
    0.46
     circonstances
    0.45
     prywat
    0.45
     வலிய
    0.45
     የበለጠ
    0.44
     욕
    0.43
    游泳
    0.43
    损害
    0.43
    Activations Density 0.002%

    No Known Activations