© 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. 209577
    Prev
    Next
    INDEX
    Explanations

    https links

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

    referral sources

    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
    .
    0.52
    hf
    0.49
     lleg
    0.48
    .")]
    0.47
    cb
    0.47
     volont
    0.47
    '
    0.47
     ሁ
    0.46
    }){
    0.46
     これ
    0.45
    POSITIVE LOGITS
    ೆಯೇ
    0.50
     MATTER
    0.47
    脨
    0.46
    धरी
    0.44
     Runway
    0.43
     Conductivity
    0.42
     Campground
    0.42
    ளுக்கும்
    0.42
    치는
    0.42
     MINISTRY
    0.42
    Activations Density 0.001%

    No Known Activations