© 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. 22-GEMMASCOPE-RES-131K
    7. 73307
    Prev
    Next
    INDEX
    Explanations

    description of a product

    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_22/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
     Terkait
    -1.34
     Envío
    -1.24
     Vainqueur
    -1.23
     mojej
    -1.20
     fote
    -1.19
    crizione
    -1.18
    جين
    -1.17
    ຣ
    -1.17
     marki
    -1.17
    فران
    -1.16
    POSITIVE LOGITS
     your
    1.76
     you
    1.71
     also
    1.33
     You
    1.25
    You
    1.19
    Your
    1.14
     We
    1.13
     U
    1.10
    We
    1.10
     our
    1.05
    Activations Density 0.006%

    No Known Activations