© 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. 69031
    Prev
    Next
    INDEX
    Explanations

    man page or command

    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
    鹮
    -2.44
     jezt
    -2.30
     ſever
    -2.20
    Dữ
    -2.14
     unſ
    -2.13
    嘡
    -2.13
     denkt
    -2.05
     innych
    -1.98
    乸
    -1.98
     Anſ
    -1.97
    POSITIVE LOGITS
    D
    2.38
    </sup>
    2.27
    m
    2.14
     is
    2.11
     Presently
    2.06
     eerie
    2.06
     exquisitely
    2.03
     Practically
    2.02
     Would
    2.00
    謁
    1.98
    Activations Density 0.017%

    No Known Activations