© 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. 135489
    Prev
    Next
    INDEX
    Explanations

    animals

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

    essential for, ongoing commissioning, moon approached, intentional data, all prime

    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
    랐
    0.50
    埌
    0.50
     xhrObj
    0.48
     positrons
    0.45
    めて
    0.43
    鎸
    0.43
     گرم
    0.43
    nesday
    0.43
     ప్రభుత్వం
    0.43
     ಅದನ್ನು
    0.43
    POSITIVE LOGITS
    ל
    0.48
    ров
    0.46
    мара
    0.44
    ं
    0.44
     win
    0.44
     wanna
    0.44
     Show
    0.42
     maneuver
    0.42
     yield
    0.42
    evin
    0.41
    Activations Density 0.000%

    No Known Activations