© 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. 195727
    Prev
    Next
    INDEX
    Explanations

    space preserve

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

    storage partitions or locations

    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
    
    0.50
    kfollowers
    0.49
    )^{[\
    0.49
    狯
    0.47
    EventRecorder
    0.46
    摖
    0.46
    hattim
    0.46
    闂
    0.46
    糍
    0.45
    versive
    0.44
    POSITIVE LOGITS
     bow
    0.53
    ป
    0.53
     చ
    0.47
    LE
    0.46
     Way
    0.46
    И
    0.46
     OTHER
    0.46
     nasty
    0.45
     dank
    0.45
    O
    0.45
    Activations Density 0.000%

    No Known Activations