© 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. 102085
    Prev
    Next
    INDEX
    Explanations

    coast, Fisher, power, obtaining, co, pantry, while, back

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

    premise is flawed

    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
    সমা
    0.51
    K
    0.50
    ۳
    0.50
     opérateurs
    0.49
    V
    0.48
    ۸
    0.48
    Wenn
    0.47
     Blick
    0.47
    dé
    0.47
    ８
    0.47
    POSITIVE LOGITS
    тите
    0.48
     crates
    0.44
    чё
    0.44
     hilly
    0.43
     coyote
    0.43
     შეგი
    0.43
     햇
    0.43
     డా
    0.42
    riteria
    0.42
     sarcastic
    0.42
    Activations Density 0.001%

    No Known Activations