© 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. 22255
    Prev
    Next
    INDEX
    Explanations

    railway station names

    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
     conozco
    -1.73
     necesito
    -1.48
    mathrm
    -1.38
     entiendo
    -1.32
     pido
    -1.30
     tuve
    -1.26
    celotti
    -1.23
    </em>
    -1.20
    </u>
    -1.20
    ://
    -1.20
    POSITIVE LOGITS
     to
    1.60
    🔃
    1.41
    峮
    1.30
     cyclisme
    1.24
     and
    1.23
     zaterdag
    1.20
     or
    1.19
     beschik
    1.16
     betrek
    1.13
     vrijdag
    1.12
    Activations Density 0.127%

    No Known Activations