© 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. 101513
    Prev
    Next
    INDEX
    Explanations

    preset settings or configurations

    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
     to
    -2.67
     avevano
    -2.45
    潆
    -2.41
    }
    -2.41
    馓
    -2.39
    鲞
    -2.36
    .
    -2.33
    ⩖
    -2.33
     dieci
    -2.31
     we
    -2.27
    POSITIVE LOGITS
    鏨
    2.64
    They
    2.38
     möjlighet
    2.34
     innebär
    2.25
     föränd
    2.13
     increasing
    2.13
     domés
    2.11
    嫫
    2.06
    دى
    2.06
     möj
    2.06
    Activations Density 0.002%

    No Known Activations