© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 21763
    Prev
    Next
    INDEX
    Explanations

    Gale, GTX, 麻烦, Sali

    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
    ’
    -3.27
    The
    -3.13
    "
    -3.02
    u
    -2.88
    ;”
    -2.70
    </sup>
    -2.67
     faſt
    -2.45
    It
    -2.42
    K
    -2.41
    庒
    -2.39
    POSITIVE LOGITS
    ization
    2.42
    }
    2.31
    neder
    2.22
    AutoresizingMask
    2.19
    indari
    2.17
    ity
    2.13
    nın
    2.11
    Ꮸ
    2.11
    鲀
    2.11
     écrit
    2.08
    Activations Density 0.059%

    No Known Activations