© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 10630
    Prev
    Next
    INDEX
    Explanations

    linked preceding words

    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
     but
    -1.60
     and
    -1.56
     Although
    -1.48
     Since
    -1.43
    2
    -1.40
     large
    -1.39
     Despite
    -1.39
     in
    -1.39
    },
    -1.38
     with
    -1.33
    POSITIVE LOGITS
     ส์
    1.82
    鲧
    1.75
    紧接着
    1.63
     serre
    1.59
     cursus
    1.57
     diriger
    1.55
     particules
    1.55
     hessen
    1.55
     your
    1.52
     commerci
    1.52
    Activations Density 0.220%

    No Known Activations