© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 87198
    Prev
    Next
    INDEX
    Explanations

    use of care and referral

    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
    ี่
    -1.34
     negru
    -1.19
    quele
    -1.16
     roba
    -1.09
     cinqu
    -1.06
    ➎
    -1.04
    The
    -1.03
     Suomessa
    -1.02
     hecta
    -1.02
    -<
    -1.01
    POSITIVE LOGITS
     to
    2.25
     svoje
    1.44
    jedno
    1.34
     fría
    1.29
     atractiva
    1.27
     sadece
    1.26
     compleja
    1.26
     deň
    1.23
     vaš
    1.22
     verdaderas
    1.22
    Activations Density 0.106%

    No Known Activations