© 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. 14923
    Prev
    Next
    INDEX
    Explanations

    data, object, param, context, tags

    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
     gelungen
    -1.32
     without
    -1.31
     earliest
    -1.25
     Männern
    -1.24
     currently
    -1.21
     natür
    -1.16
     дорога
    -1.16
     episode
    -1.15
     stück
    -1.14
     early
    -1.13
    POSITIVE LOGITS
    𝗥
    1.61
    вана
    1.50
    ();
    1.48
    ]),
    1.45
    ;
    1.45
    ('%
    1.44
    ۔
    1.44
     Polícia
    1.41
    ੧
    1.41
    踵
    1.39
    Activations Density 0.008%

    No Known Activations