© 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. 131267
    Prev
    Next
    INDEX
    Explanations

    crusher, grinding, finish

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

    react problem statement

    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
    د
    0.54
     crawled
    0.52
     crawling
    0.47
    自治
    0.46
    だから
    0.46
    lardan
    0.46
    d
    0.46
     स्वातंत्र
    0.45
    под
    0.45
    س
    0.44
    POSITIVE LOGITS
    άνει
    0.46
     slu
    0.46
     ဆို
    0.45
     ኢ
    0.44
    leValue
    0.44
     functionality
    0.43
    ießen
    0.43
     шла
    0.42
     Sweden
    0.41
    ACIONES
    0.41
    Activations Density 0.001%

    No Known Activations