© 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. 41200
    Prev
    Next
    INDEX
    Explanations

    Apache License, Version

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

    version numbers and categories

    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
     elongation
    0.46
     Mili
    0.44
     感じ
    0.44
     forex
    0.42
    ׳
    0.42
     fulfilment
    0.41
     headlines
    0.41
     Egi
    0.41
    ی
    0.40
     evaluations
    0.40
    POSITIVE LOGITS
    atán
    0.45
    ளாவ
    0.45
    ლა
    0.44
    沁
    0.40
    尔多
    0.40
     isTestSource
    0.40
     эксплуа
    0.39
    涌
    0.39
     ATG
    0.39
    tracks
    0.39
    Activations Density 0.000%

    No Known Activations