© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 71305
    Prev
    Next
    INDEX
    Explanations

    disappointment stems

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

    Docker socket, prompt, DID, checking

    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
    Negative Logits
    tones
    0.55
     =
    0.50
     juin
    0.49
    စား
    0.48
    tt
    0.47
    ts
    0.47
    defer
    0.46
     begun
    0.45
    m
    0.45
    tidy
    0.45
    POSITIVE LOGITS
     Сим
    0.49
     Gesamt
    0.47
     솔
    0.47
     ارشاد
    0.46
     Artikel
    0.45
     Prozess
    0.45
    ប្រស
    0.45
     Zusatz
    0.45
     ఆది
    0.44
     সমগ্র
    0.44
    Activations Density 0.002%

    No Known Activations