© 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. 35182
    Prev
    Next
    INDEX
    Explanations

    comparative descriptions

    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
     INTERVAL
    -1.12
     pertumbuhan
    -1.12
     inflam
    -1.09
     込
    -1.09
    льд
    -1.09
    alugar
    -1.07
     perfecte
    -1.07
     شناسی
    -1.06
     purée
    -1.06
     ingredi
    -1.06
    POSITIVE LOGITS
     than
    2.02
    mstyle
    1.27
     niż
    1.24
    than
    1.20
    itemize
    1.14
    }}\
    1.13
     version
    1.12
    ätter
    1.08
     wersja
    1.07
     unangemessene
    1.06
    Activations Density 0.033%

    No Known Activations