© 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. 199607
    Prev
    Next
    INDEX
    Explanations

    positions

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

    algorithm, understand, symbolize

    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
     study
    0.48
     horário
    0.46
    يّ
    0.46
    ُ
    0.45
     diadakan
    0.45
    िन
    0.45
     referendum
    0.45
    لو
    0.45
    笘
    0.44
     یو
    0.43
    POSITIVE LOGITS
     Axel
    0.53
    Lng
    0.48
    '
    0.47
     krypt
    0.46
     hexagons
    0.46
     ఉత్ప
    0.45
    ⋮
    0.45
     Jordi
    0.45
    dro
    0.44
     etiquetas
    0.44
    Activations Density 0.001%

    No Known Activations