© 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. 100133
    Prev
    Next
    INDEX
    Explanations

    physical attributes and measurements

    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
     chanson
    -1.26
     Réseau
    -1.23
    }}
    -1.18
     tirs
    -1.16
     ),
    -1.16
     ruines
    -1.15
     ruine
    -1.14
    tação
    -1.11
     côtes
    -1.11
    meld
    -1.10
    POSITIVE LOGITS
     también
    1.72
     também
    1.48
    也可以
    1.47
     also
    1.44
    也要
    1.30
    いいですね
    1.27
     ebenfalls
    1.23
     ALSO
    1.22
     نیز
    1.20
     detención
    1.20
    Activations Density 0.230%

    No Known Activations