© 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. 39540
    Prev
    Next
    INDEX
    Explanations

    desperate searches, attempts, or needs

    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
    嚶
    -3.13
    Groet
    -2.67
    厹
    -2.64
    很難
    -2.59
    ementara
    -2.58
    ⵈ
    -2.53
    튿
    -2.52
    訁
    -2.48
    ⢊
    -2.45
     eſſ
    -2.41
    POSITIVE LOGITS
    0
    4.19
    ’
    3.08
    ”,
    3.06
    ”
    3.03
    .
    2.97
    a
    2.58
    ↵
    2.44
    an
    2.39
     “
    2.38
     (“
    2.38
    Activations Density 0.003%

    No Known Activations