© 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. 175210
    Prev
    Next
    INDEX
    Explanations

    Spanish Two, verify, reform, view

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

    cutting ties, logging, gravity

    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
     encourages
    0.52
    ور
    0.47
     Ensures
    0.46
     Prayers
    0.45
    ڈی
    0.45
     A
    0.45
     successors
    0.45
     Label
    0.44
     jokes
    0.44
     encouragement
    0.43
    POSITIVE LOGITS
    作战
    0.47
    Penis
    0.46
    “-
    0.46
     penis
    0.46
     MEXICO
    0.46
    廡
    0.46
    Mexico
    0.45
     netto
    0.45
     vzdu
    0.45
    UGG
    0.44
    Activations Density 0.000%

    No Known Activations