© 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. 38846
    Prev
    Next
    INDEX
    Explanations

    Assessment of[Study ofThe occasional

    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
     on
    -2.31
     by
    -1.91
     also
    -1.88
     in
    -1.79
     or
    -1.55
     without
    -1.47
     during
    -1.46
     while
    -1.41
     additional
    -1.40
     it
    -1.37
    POSITIVE LOGITS
     bandar
    1.54
    裆
    1.54
     kuu
    1.46
     sekarang
    1.45
     talle
    1.41
    Increasing
    1.38
    いま
    1.38
     خوبه
    1.34
    ſo
    1.33
    うーん
    1.32
    Activations Density 0.000%

    No Known Activations