© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13570
    Prev
    Next
    INDEX
    Explanations

    mozilla developer urls

    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
    的所有
    -2.05
    ".
    -2.05
     and
    -2.05
    \
    -1.98
     desolate
    -1.98
     exquisitely
    -1.95
    でした
    -1.90
    м
    -1.88
     diffic
    -1.86
     azure
    -1.86
    POSITIVE LOGITS
    ing
    2.94
     a
    2.88
    がたくさん
    2.63
     Hinblick
    2.53
     estekak
    2.44
    }
    2.39
    猻
    2.19
     "}
    2.16
     besonder
    2.13
     spannend
    2.09
    Activations Density 0.018%

    No Known Activations