© 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. 84051
    Prev
    Next
    INDEX
    Explanations

    inline rsp, Handles colors, look grand, AS ASIC, MINUTE OF, Dear Sir

    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
    opress
    -1.52
     kwamba
    -1.51
     çünkü
    -1.49
    要不然
    -1.45
    }$,
    -1.45
     who
    -1.45
     Söhne
    -1.45
    äus
    -1.41
     Güter
    -1.40
     vektör
    -1.39
    POSITIVE LOGITS
     but
    2.00
     яйцо
    1.73
     negó
    1.65
     книг
    1.63
    š
    1.54
    Sinopse
    1.52
     entregó
    1.52
    謚
    1.52
     ordenó
    1.51
     Istri
    1.49
    Activations Density 0.009%

    No Known Activations