© 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. 71078
    Prev
    Next
    INDEX
    Explanations

    Toronto entities

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    }
    -2.86
    i
    -2.84
    ',
    -2.75
    4
    -2.73
    on
    -2.66
    躂
    -2.47
    這個
    -2.45
    樒
    -2.41
    3
    -2.36
    8
    -2.36
    POSITIVE LOGITS
    逦
    3.58
    欒
    2.70
     Saltar
    2.63
    鈊
    2.58
    鹚
    2.36
    poptotic
    2.33
     形象
    2.25
    べく
    2.25
    </h2>
    2.22
    ⼒
    2.22
    Activations Density 0.004%

    No Known Activations