© 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. 128934
    Prev
    Next
    INDEX
    Explanations

    AMD hardware and company

    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
    as
    -2.55
    itsubishi
    -2.41
    '
    -2.39
    ).
    -2.36
     региона
    -2.34
     Then
    -2.28
     entonces
    -2.28
    」
    -2.20
    </h3>
    -2.14
     également
    -2.13
    POSITIVE LOGITS
    𓍊
    3.14
    渽
    2.84
    which
    2.75
     wichtige
    2.73
    筇
    2.66
    銪
    2.61
    泐
    2.52
    觧
    2.52
    舠
    2.50
    zation
    2.48
    Activations Density 0.001%

    No Known Activations