© 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. 21277
    Prev
    Next
    INDEX
    Explanations

    Rochester, NSMutable

    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
    5
    -3.53
    1
    -3.47
    3
    -3.41
     
    -3.39
    :
    -3.33
    2
    -3.30
    4
    -3.28
    9
    -3.27
    THE
    -3.23
    A
    -2.95
    POSITIVE LOGITS
    鋮
    3.17
    仉
    2.98
    幛
    2.97
    ᠂
    2.78
    嫱
    2.77
    闞
    2.75
    鹩
    2.72
    拶
    2.67
    。
    2.64
    ⎚
    2.63
    Activations Density 0.004%

    No Known Activations