© 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. 67471
    Prev
    Next
    INDEX
    Explanations

    Internet citations

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

    internal commands or errors

    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
    Jet
    0.57
     Jet
    0.54
    ジェット
    0.49
     jet
    0.48
    getMain
    0.47
    緹
    0.47
     paymentRequest
    0.46
     保
    0.46
    JET
    0.45
     BlogPost
    0.44
    POSITIVE LOGITS
    intern
    0.54
     Intern
    0.53
     interns
    0.51
    internal
    0.49
     intern
    0.48
    adv
    0.46
     interne
    0.45
    Intern
    0.44
     internas
    0.43
     internals
    0.42
    Activations Density 0.009%

    No Known Activations