© 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. 195974
    Prev
    Next
    INDEX
    Explanations

    unscrew

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

    decaying organic, cooked chicken

    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
    Creating
    0.52
    xticks
    0.51
    Goodbye
    0.47
    ட்டாக
    0.47
    Generate
    0.47
    첸
    0.47
    pré
    0.46
    Repeating
    0.45
    Six
    0.45
    creating
    0.45
    POSITIVE LOGITS
     Americans
    0.50
     commons
    0.48
     US
    0.45
     Zi
    0.45
     Klan
    0.45
     North
    0.45
     UNA
    0.45
     U
    0.45
     General
    0.44
     一般
    0.44
    Activations Density 0.003%

    No Known Activations