© 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. 202865
    Prev
    Next
    INDEX
    Explanations

    claim or defense

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

    Python script

    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
     داشته
    0.50
     matriline
    0.46
     وع
    0.46
     aparece
    0.46
     toneladas
    0.46
     estará
    0.45
    복
    0.45
    ラン
    0.45
     effluents
    0.45
     tendrá
    0.45
    POSITIVE LOGITS
    ந்தை
    0.45
     Hee
    0.44
     Sydney
    0.43
    ao
    0.42
    Ọ
    0.42
     Tees
    0.41
    deling
    0.41
    adjacent
    0.40
     Java
    0.40
    িষ
    0.40
    Activations Density 0.001%

    No Known Activations