© 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. 25036
    Prev
    Next
    INDEX
    Explanations

    from certain words

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

    objects and actions

    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
     dame
    0.50
    いため
    0.48
    }{
    0.48
    findBy
    0.47
    ile
    0.47
    이면
    0.46
    Set
    0.46
     這個
    0.46
     ლი
    0.45
     时
    0.45
    POSITIVE LOGITS
     secretions
    0.47
    简介
    0.46
    اتے
    0.45
     monolayers
    0.45
     sediments
    0.45
     yanı
    0.45
     superficially
    0.44
     Shrewsbury
    0.44
     reformulated
    0.44
     bedrooms
    0.44
    Activations Density 0.000%

    No Known Activations