© 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. 189638
    Prev
    Next
    INDEX
    Explanations

    skid plates, funnel, research, applied, times, pigs

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

    building materials

    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
    onto
    0.49
    a
    0.44
     onto
    0.42
     klant
    0.42
     ont
    0.41
    onic
    0.41
     terug
    0.41
    B
    0.40
    oby
    0.40
    ക്കെ
    0.40
    POSITIVE LOGITS
    ンスター
    0.48
     PluginResult
    0.47
    貉
    0.46
     scraper
    0.46
    রাসের
    0.46
    类似于
    0.46
    irea
    0.44
    耄
    0.44
     gră
    0.44
     '*'
    0.43
    Activations Density 0.002%

    No Known Activations