© 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. 22-GEMMASCOPE-RES-131K
    7. 74975
    Prev
    Next
    INDEX
    Explanations

    Normal localization metadata

    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
    camion
    -1.32
     εδώ
    -1.31
    Rha
    -1.17
    Terminology
    -1.15
    Kond
    -1.13
     miesięcy
    -1.13
    Questionnaire
    -1.11
    uç
    -1.10
    fortnite
    -1.09
    裡的
    -1.09
    POSITIVE LOGITS
    =?,
    1.29
     \_
    1.25
     ',
    1.22
     cujo
    1.20
    ANEOUS
    1.18
    ificance
    1.16
    IST
    1.16
    \%,
    1.16
    od
    1.15
     \#
    1.14
    Activations Density 0.061%

    No Known Activations