© 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. 196969
    Prev
    Next
    INDEX
    Explanations

    Getty Center, Victorian Dance

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

    foreign and numbered lists

    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
    {
    0.52
    &:
    0.50
    .&
    0.49
    \|=
    0.48
     toddlers
    0.46
    efficients
    0.45
     IV
    0.44
    dun
    0.44
     speciali
    0.43
     мем
    0.43
    POSITIVE LOGITS
    兰
    0.53
    随着
    0.52
    以
    0.52
    薗
    0.52
    极
    0.50
    诮
    0.50
    领域
    0.50
     след
    0.50
    很
    0.49
    給
    0.49
    Activations Density 0.001%

    No Known Activations