© 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. 56205
    Prev
    Next
    INDEX
    Explanations

    HTTPS protocol

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

    enslaved people

    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
    acquisto
    0.47
     மூன்று
    0.45
    ributing
    0.44
     Simple
    0.41
     அடிப்படையில்
    0.41
    Ņ
    0.41
     ત્રણ
    0.40
    ‥
    0.40
     ра
    0.40
    
    0.40
    POSITIVE LOGITS
     fucked
    0.52
     diffract
    0.50
     looks
    0.48
     tembok
    0.46
     poses
    0.45
     minta
    0.44
     uptick
    0.42
     came
    0.41
    ထိ
    0.41
     fluctuates
    0.40
    Activations Density 0.000%

    No Known Activations