© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101814
    Prev
    Next
    INDEX
    Explanations

    local file paths

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

    Windows file path separators (backslashes).

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sebagainya
    -1.86
    RICS
    -1.81
    ⇹
    -1.77
    🪆
    -1.70
     otros
    -1.68
    いえば
    -1.67
     žen
    -1.61
    甗
    -1.61
    言えば
    -1.58
    𓆝
    -1.55
    POSITIVE LOGITS
     /
    2.02
     it
    1.95
    Максим
    1.65
    !
    1.55
     में
    1.45
    鬱
    1.44
    in
    1.44
     inspiri
    1.41
     Если
    1.40
     hermosas
    1.38
    Activations Density 0.012%

    No Known Activations