© 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. 143813
    Prev
    Next
    INDEX
    Explanations

    problems, assignments, or website requests

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

    Superior Spider-Man

    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
    窣
    0.51
    َّا
    0.47
     közö
    0.44
    حدة
    0.42
    蓍
    0.41
    öh
    0.41
    津
    0.41
    Speak
    0.41
     Kazan
    0.40
    ++;//
    0.40
    POSITIVE LOGITS
     for
    0.53
     find
    0.52
    at
    0.52
    সই
    0.51
    dark
    0.48
    л
    0.48
    problem
    0.47
    figcaption
    0.47
     antics
    0.47
     pcs
    0.47
    Activations Density 0.001%

    No Known Activations