© 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. 94729
    Prev
    Next
    INDEX
    Explanations

    patent numbers and identifiers

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

    urls to educational resources

    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
    Ș
    0.48
    ћа
    0.47
     이번
    0.46
    𝗣
    0.44
    чиго
    0.43
    이번
    0.43
    گیز
    0.42
    РО
    0.42
    ENTA
    0.42
    섀
    0.42
    POSITIVE LOGITS
     Acupuncture
    0.43
     http
    0.42
     Iceland
    0.41
     Scientific
    0.41
     Undergraduate
    0.41
     damals
    0.40
     Calcular
    0.40
     Mathematical
    0.40
     Calculating
    0.40
     Blog
    0.39
    Activations Density 0.013%

    No Known Activations