© 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. 193644
    Prev
    Next
    INDEX
    Explanations

    years of experience

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

    linear regression and least squares method

    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
     evade
    0.55
    他
    0.54
    жают
    0.52
     அவன்
    0.45
    🤣🤣
    0.45
     unsatisf
    0.45
     aquella
    0.45
     evaded
    0.45
    一线
    0.44
    엥
    0.44
    POSITIVE LOGITS
     Ber
    0.50
    暉
    0.48
     conspicuous
    0.47
     Bl
    0.47
     PURPOSE
    0.47
     FER
    0.47
     Mark
    0.46
     Marc
    0.46
     Tote
    0.46
     Sets
    0.45
    Activations Density 0.001%

    No Known Activations