© 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. 21528
    Prev
    Next
    INDEX
    Explanations

    direction into

    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
     of
    -1.98
    ”？
    -1.80
     этих
    -1.67
    ”（
    -1.64
     liknande
    -1.61
     nacidos
    -1.57
     его
    -1.55
     необходимые
    -1.55
     wichtige
    -1.54
    bbons
    -1.53
    POSITIVE LOGITS
     our
    1.90
     the
    1.60
     their
    1.50
     an
    1.46
    踯
    1.45
     any
    1.43
    ⿵
    1.41
     rechte
    1.34
     芋
    1.33
     labd
    1.33
    Activations Density 0.039%

    No Known Activations