© 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. 107654
    Prev
    Next
    INDEX
    Explanations

    called upon

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

    hardware/data identifiers

    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
     vestidos
    0.49
    넥
    0.48
     largos
    0.46
     nurseries
    0.46
    Vinyl
    0.46
    ام
    0.45
     trasera
    0.45
     sleeveless
    0.44
     panties
    0.44
     dérivés
    0.43
    POSITIVE LOGITS
    '،
    0.49
     ख
    0.48
    ,’
    0.48
    ricane
    0.47
    lobulin
    0.47
     انھوں
    0.46
    conference
    0.46
     सच्चे
    0.46
    olni
    0.46
    '(
    0.45
    Activations Density 0.001%

    No Known Activations