© 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. 186064
    Prev
    Next
    INDEX
    Explanations

    people's names and media roles

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

    technical terms and names

    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
    В
    0.51
    История
    0.49
     Му
    0.46
    С
    0.45
    専門
    0.45
     В
    0.45
    గా
    0.45
    사
    0.44
    徬
    0.44
    REPO
    0.44
    POSITIVE LOGITS
    mero
    0.50
     hudson
    0.49
    hemer
    0.49
     Elwood
    0.49
    meros
    0.47
     Weaver
    0.46
     Clayton
    0.44
     ខ
    0.44
    检索
    0.44
    currentColor
    0.43
    Activations Density 0.001%

    No Known Activations