© 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. 6528
    Prev
    Next
    INDEX
    Explanations

    numbers followed by units or identifiers

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

    environment variables and code indices

    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
     kurzer
    0.17
     choroby
    0.16
    NgramModel
    0.15
     måtte
    0.15
     stoichi
    0.15
    خرى
    0.14
    龋
    0.14
    GALAD
    0.14
    ÉRI
    0.14
     geschaffen
    0.14
    POSITIVE LOGITS
    As
    0.18
    S
    0.17
     As
    0.16
     In
    0.15
     Setting
    0.15
     Be
    0.14
    ="",
    0.14
     Goal
    0.14
     Access
    0.14
    С
    0.14
    Activations Density 0.193%

    No Known Activations