© 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. 10-GEMMASCOPE-RES-131K
    7. 129152
    Prev
    Next
    INDEX
    Explanations

    least one of

    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
    笮
    -1.24
    za
    -1.22
    咐
    -1.20
     nara
    -1.20
    高质量
    -1.18
    endfor
    -1.16
     plak
    -1.16
     cij
    -1.16
    ndash
    -1.15
     prak
    -1.14
    POSITIVE LOGITS
     any
    2.16
     or
    1.73
     this
    1.68
     the
    1.66
     how
    1.57
     both
    1.53
     each
    1.49
     either
    1.42
     you
    1.37
     However
    1.37
    Activations Density 0.025%

    No Known Activations