© 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. 209281
    Prev
    Next
    INDEX
    Explanations

    about the birthplace

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

    hands, yourself, about connection

    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
    لود
    0.50
    ées
    0.49
     পরিষে
    0.48
     রম
    0.48
    룹
    0.48
    øy
    0.47
    드
    0.47
    és
    0.47
     stagione
    0.46
     godina
    0.46
    POSITIVE LOGITS
    Traversal
    0.48
     demoral
    0.44
    clang
    0.43
    人を
    0.42
     WHILE
    0.42
    Similarity
    0.42
    sieh
    0.42
     saurait
    0.42
    Psalm
    0.42
    balls
    0.41
    Activations Density 0.000%

    No Known Activations