© 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. 212234
    Prev
    Next
    INDEX
    Explanations

    whiningdefensereal

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

    business details and transactions

    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
     in
    0.56
     т
    0.52
     where
    0.52
     considered
    0.51
     в
    0.50
     д
    0.48
     d
    0.48
     staffed
    0.48
     there
    0.48
     द
    0.48
    POSITIVE LOGITS
    camel
    0.51
    ارب
    0.50
    ِب
    0.49
    عيه
    0.49
    NeedConnect
    0.47
    ből
    0.47
    気に入り
    0.46
     automatiquement
    0.45
     انته
    0.45
    َة
    0.44
    Activations Density 0.001%

    No Known Activations