© 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. 112541
    Prev
    Next
    INDEX
    Explanations

    simple. A baby. Bergen. CDC. complete. you

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

    interviewed by, arts traditions

    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
    ία
    0.50
    פ
    0.48
    缡
    0.47
    ла
    0.44
     белару
    0.44
    лага
    0.44
     senator
    0.43
     bagel
    0.43
    ጵ
    0.43
     депута
    0.42
    POSITIVE LOGITS
    atsuki
    0.49
    mos
    0.48
    search
    0.47
    result
    0.47
    storage
    0.47
    fun
    0.46
    model
    0.46
    sequences
    0.46
    hy
    0.46
    mer
    0.46
    Activations Density 0.001%

    No Known Activations