© 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. 34-GEMMASCOPE-RES-131K
    7. 64914
    Prev
    Next
    INDEX
    Explanations

    data/code delimiters

    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_34/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
     in
    -1.30
    ERÍA
    -1.14
    moderne
    -1.13
    batterie
    -1.13
     mengganggu
    -1.10
    komme
    -1.09
    cuencia
    -1.07
     that
    -1.03
     Meningkatkan
    -1.02
     häm
    -1.02
    POSITIVE LOGITS
     immense
    1.29
     zweimal
    1.27
     mitge
    1.20
     tumultuous
    1.20
     momentous
    1.19
     alluring
    1.17
     dilapidated
    1.16
     angefü
    1.14
     (\<
    1.13
     shimmering
    1.12
    Activations Density 0.001%

    No Known Activations