© 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. 233517
    Prev
    Next
    INDEX
    Explanations

    locations

    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
     ScriptInterface
    0.47
    ঙ্কর
    0.47
    亼
    0.44
    ங்களைப்
    0.44
    하도록
    0.43
    皇家
    0.43
    旂
    0.43
     Jamal
    0.43
     आरमारा
    0.43
     to
    0.42
    POSITIVE LOGITS
    ה
    0.46
     order
    0.44
     evacu
    0.44
     finiteness
    0.44
    <code>
    0.43
    ه
    0.42
    <0xAC>
    0.41
    <0xF3>
    0.41
    あくまで
    0.41
    .........
    0.41
    Activations Density 0.001%

    No Known Activations