© 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. 7744
    Prev
    Next
    INDEX
    Explanations

    ranking numbers

    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
     که
    -1.84
     που
    -1.72
    }
    -1.70
     två
    -1.59
     zwanzig
    -1.55
    },
    -1.51
    その
    -1.51
    年来
    -1.48
    ),
    -1.48
    这些
    -1.48
    POSITIVE LOGITS
    </h2>
    1.59
    しっかりと
    1.43
     '';
    1.38
     vegeta
    1.34
     something
    1.31
     on
    1.29
     priva
    1.29
     only
    1.27
     what
    1.25
     viu
    1.25
    Activations Density 0.015%

    No Known Activations