© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34507
    Prev
    Next
    INDEX
    Explanations

    spanish forums

    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
     السياس
    -1.59
     BSEB
    -1.55
     Andante
    -1.54
     monstru
    -1.48
    ❗️
    -1.44
    ଶ
    -1.41
     Dinas
    -1.40
     allan
    -1.40
    <bos>
    -1.39
     bof
    -1.39
    POSITIVE LOGITS
     all
    1.61
     our
    1.43
     every
    1.41
     your
    1.34
     some
    1.33
     v
    1.30
     k
    1.30
     my
    1.30
     confirmar
    1.28
     everything
    1.27
    Activations Density 0.106%

    No Known Activations