© 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. 22-GEMMASCOPE-RES-131K
    7. 65075
    Prev
    Next
    INDEX
    Explanations

    clock configuration and divisors

    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_22/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
    typeDefinition
    -1.28
    parsedMessage
    -1.27
     instituciones
    -1.24
     ಪ್ರ
    -1.20
     discí
    -1.17
    %;
    -1.14
     CHtml
    -1.14
    சிய
    -1.13
    ريقة
    -1.13
    featureID
    -1.13
    POSITIVE LOGITS
     ویت
    1.30
     gorro
    1.22
     assertive
    1.10
    竊
    1.10
    声が
    1.08
    了几
    1.08
     Ostra
    1.08
    \
    1.08
    *
    1.07
    犧
    1.06
    Activations Density 0.007%

    No Known Activations