© 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. 99035
    Prev
    Next
    INDEX
    Explanations

    through a means

    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
    濑
    -1.38
     cuando
    -1.29
    てて
    -1.27
    节省
    -1.19
    臓
    -1.17
    遑
    -1.17
    讴
    -1.17
    えています
    -1.16
    窺
    -1.15
    처럼
    -1.13
    POSITIVE LOGITS
    puts
    2.13
     the
    1.98
     careful
    1.95
     a
    1.58
     VARIOUS
    1.56
     their
    1.55
    Various
    1.53
    various
    1.48
     various
    1.48
     our
    1.44
    Activations Density 0.039%

    No Known Activations