© 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. 86276
    Prev
    Next
    INDEX
    Explanations

    mathematical calculations and results

    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
    everything
    -1.50
    vertebrates
    -1.45
    tifications
    -1.30
    whatever
    -1.30
    lorn
    -1.28
    Everything
    -1.27
    ueroa
    -1.27
    ServletException
    -1.26
     such
    -1.24
     baik
    -1.24
    POSITIVE LOGITS
     a
    1.51
     aproximativ
    1.45
    })=
    1.38
    »).
    1.34
     verwijderen
    1.32
    了一口
    1.30
    producción
    1.30
    </h4>
    1.29
     Schluß
    1.29
     Grundstück
    1.27
    Activations Density 0.036%

    No Known Activations