© 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. 17
    Prev
    Next
    INDEX
    Explanations

    dexterity, supple, unexamined, Alfonso, Crawley

    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
    '
    -3.92
    </strong>
    -2.95
    h
    -2.48
    N
    -2.28
    is
    -2.28
    ar
    -2.23
    le
    -2.20
     We
    -2.19
    z
    -2.02
     但
    -2.00
    POSITIVE LOGITS
    ’
    3.80
    ”،
    3.05
    ’，
    2.83
    🪤
    2.83
     Eigentü
    2.66
    ейчас
    2.52
    rientes
    2.50
    🦤
    2.50
     夾
    2.44
    玊
    2.44
    Activations Density 0.006%

    No Known Activations