© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26466
    Prev
    Next
    INDEX
    Explanations

    military forces and actions

    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
    Each
    -1.34
    There
    -1.30
    To
    -1.14
    This
    -1.13
    It
    -1.12
    ʋ
    -1.11
    Also
    -1.11
    nictví
    -1.10
    графії
    -1.10
    Activités
    -1.10
    POSITIVE LOGITS
     assembled
    1.35
     against
    1.26
    ामी
    1.17
    iress
    1.16
     of
    1.16
    Память
    1.15
     strength
    1.14
     daug
    1.13
    淬
    1.11
    哧
    1.07
    Activations Density 0.023%

    No Known Activations