© 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. 136610
    Prev
    Next
    INDEX
    Explanations

    options month save colourful system complete

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

    vector x, control, compression

    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
    ↵↵
    0.72
     Tribes
    0.48
    hline
    0.46
     Tribune
    0.42
    Trib
    0.42
    ocket
    0.41
    olique
    0.40
    parsing
    0.40
    ↵
    0.39
     tribal
    0.39
    POSITIVE LOGITS
     ಖರೀದ
    0.58
     voltou
    0.58
    ཋ
    0.56
    ção
    0.56
     cuid
    0.56
    រួ
    0.55
    𝗗
    0.55
     secundaria
    0.55
    ای
    0.54
     elevada
    0.52
    Activations Density 0.000%

    No Known Activations