© 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. 71145
    Prev
    Next
    INDEX
    Explanations

    the number 13

    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
    ologies
    -1.72
    ſſer
    -1.65
    ing
    -1.63
     optique
    -1.62
    tedrale
    -1.61
    ++];
    -1.60
    AfterViewInit
    -1.59
     دیدن
    -1.56
    resentação
    -1.54
     Murillo
    -1.52
    POSITIVE LOGITS
    '
    1.84
     zahlreichen
    1.69
     the
    1.49
    ਃ
    1.47
     our
    1.46
     umbrellas
    1.46
     wielu
    1.45
     freaking
    1.43
     poking
    1.39
     diálogo
    1.36
    Activations Density 0.013%

    No Known Activations