© 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. 158483
    Prev
    Next
    INDEX
    Explanations

    dryness, cracks, and sports

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

    common punctuation and structure words

    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
    뿌
    0.47
    ங்கிய
    0.46
    വശ
    0.45
    ಕ್ರ
    0.44
    рг
    0.43
    ტორი
    0.42
    ق
    0.42
    кру
    0.42
    જ
    0.42
    किसी
    0.41
    POSITIVE LOGITS
     admissible
    0.52
     comparisons
    0.48
     Longitudinal
    0.48
     insertions
    0.47
     analogies
    0.47
     cleats
    0.46
     texted
    0.46
     speedboat
    0.46
     transcript
    0.46
     moldings
    0.46
    Activations Density 0.001%

    No Known Activations