© 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. 201462
    Prev
    Next
    INDEX
    Explanations

    provided courtesy of

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

    configuration parameters

    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
    UTRAL
    0.47
    ื่น
    0.46
    в
    0.45
    emiah
    0.44
     Illustrated
    0.44
    जै
    0.43
    विल
    0.43
    釹
    0.43
    álisis
    0.43
    Illustrated
    0.42
    POSITIVE LOGITS
    CommonAncestor
    0.48
     majest
    0.44
     Obr
    0.44
    TreeWidgetItem
    0.44
     setzt
    0.44
     cheques
    0.43
     جوس
    0.43
    _
    0.42
     methionine
    0.42
     ORF
    0.42
    Activations Density 0.001%

    No Known Activations