© 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. 129522
    Prev
    Next
    INDEX
    Explanations

    technical or scientific context

    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
    </b>
    -1.84
     autre
    -1.49
    每个
    -1.40
    }
    -1.31
     この
    -1.22
    </i>
    -1.20
    "})
    -1.20
    </h1>
    -1.16
     aldrig
    -1.15
    We
    -1.14
    POSITIVE LOGITS
     their
    2.20
     themselves
    1.66
     various
    1.59
     decidieron
    1.39
     thier
    1.33
     piensan
    1.29
     with
    1.28
    símbolo
    1.27
     hablan
    1.27
    тивно
    1.27
    Activations Density 0.001%

    No Known Activations