© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 11463
    Prev
    Next
    INDEX
    Explanations

    code imports and libraries

    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
     evtl
    -1.05
    MIND
    -1.05
    owego
    -1.05
    !!!!!!!
    -1.05
     différents
    -1.05
    !!!!!!!!!
    -1.03
     its
    -0.99
     był
    -0.98
     verschillende
    -0.98
     xxv
    -0.95
    POSITIVE LOGITS
     berbasis
    1.17
     new
    1.11
    zondere
    1.05
     bygg
    0.99
     with
    0.98
    典型的
    0.98
    өздер
    0.97
    ֹת
    0.96
     unangemessene
    0.96
     начинается
    0.95
    Activations Density 0.015%

    No Known Activations