© 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. 7879
    Prev
    Next
    INDEX
    Explanations

    by [agent/means]

    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
     is
    -2.11
    ’
    -1.97
    .,
    -1.66
    There
    -1.48
    If
    -1.47
    Its
    -1.45
    y
    -1.45
    了一种
    -1.42
    It
    -1.40
    。《
    -1.39
    POSITIVE LOGITS
     our
    1.63
    🡺
    1.55
     podat
    1.53
    锨
    1.51
    ţei
    1.48
     you
    1.43
    可不是
    1.41
    AMIENTO
    1.41
     agradec
    1.39
     enfermera
    1.39
    Activations Density 0.011%

    No Known Activations