© 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. 39456
    Prev
    Next
    INDEX
    Explanations

    describing scenarios or conditions

    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
     potrebné
    -1.44
     aumentado
    -1.33
    ных
    -1.33
     polskiego
    -1.31
    良好的
    -1.31
    _"
    -1.30
    enschutzer
    -1.30
     ešte
    -1.26
     działalności
    -1.22
    n
    -1.22
    POSITIVE LOGITS
    </h3>
    1.43
     cinquante
    1.40
    並不是
    1.36
    łyż
    1.35
     écou
    1.32
     Parigi
    1.31
    ITHER
    1.31
     USING
    1.30
    沢山
    1.29
     is
    1.27
    Activations Density 0.052%

    No Known Activations