© 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. 22-GEMMASCOPE-RES-131K
    7. 72011
    Prev
    Next
    INDEX
    Explanations

    section markers like II. or 2

    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
     from
    -1.47
     people
    -1.33
     other
    -1.31
     larger
    -1.22
     every
    -1.18
     truly
    -1.15
     really
    -1.12
     only
    -1.12
     its
    -1.11
     during
    -1.07
    POSITIVE LOGITS
     dépenses
    1.23
    ܆
    1.13
    UnitTesting
    1.11
    튿
    1.10
     informes
    1.09
    provides
    1.09
     SEPAR
    1.06
     THOUGHT
    1.06
     inp
    1.05
    íd
    1.05
    Activations Density 0.034%

    No Known Activations