© 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. 85597
    Prev
    Next
    INDEX
    Explanations

    sweep between or followed by

    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
     i
    -3.25
    .
    -3.17
    翃
    -2.83
     he
    -2.77
     será
    -2.77
    霎
    -2.75
    }
    -2.73
     same
    -2.56
    li
    -2.56
    se
    -2.56
    POSITIVE LOGITS
    骜
    3.30
    ڧ
    3.28
    驁
    3.22
    蟶
    3.14
    鯔
    3.05
    偸
    3.03
    獁
    2.91
    谡
    2.89
     夜景
    2.81
    寕
    2.81
    Activations Density 0.004%

    No Known Activations