© 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. 128994
    Prev
    Next
    INDEX
    Explanations

    worth and valuation assessments

    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
    ContentLoaded
    -1.41
    delser
    -1.35
    Приготовление
    -1.31
    cheque
    -1.30
     Cuando
    -1.28
    elser
    -1.27
    ഃ
    -1.26
    IARC
    -1.24
     crossorigin
    -1.24
    hlar
    -1.23
    POSITIVE LOGITS
     what
    1.94
     adequate
    1.16
     how
    1.16
     why
    1.13
     because
    1.11
     appropriate
    1.10
    er
    1.03
     sufficient
    1.02
        
    1.02
     your
    1.02
    Activations Density 0.049%

    No Known Activations