© 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. 23370
    Prev
    Next
    INDEX
    Explanations

    minksculas

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

    situations and past events

    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
     እና
    0.36
     եւ
    0.33
    及
    0.33
    以及
    0.32
    และ
    0.32
     καὶ
    0.32
     ಮತ್ತು
    0.32
     మరియు
    0.32
     및
    0.32
     и
    0.31
    POSITIVE LOGITS
     encontraron
    0.39
     pediatrician
    0.34
     ماں
    0.32
     teacher
    0.32
    teacher
    0.32
     escond
    0.32
     probablement
    0.31
     Honest
    0.31
     Creek
    0.30
     professora
    0.30
    Activations Density 0.000%

    No Known Activations