© 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. 10-GEMMASCOPE-RES-131K
    7. 70189
    Prev
    Next
    INDEX
    Explanations

    clarity, certainty, and specificity

    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_10/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
     They
    -1.84
     könnten
    -1.72
     These
    -1.70
     prominently
    -1.65
    atilde
    -1.54
     scoprire
    -1.53
    合った
    -1.52
    CEEDED
    -1.51
     affitto
    -1.50
     getStatus
    -1.46
    POSITIVE LOGITS
     that
    2.42
    たまたま
    1.54
     antidesliz
    1.53
    and
    1.47
     beslut
    1.45
    to
    1.43
    媖
    1.41
    laund
    1.38
     любые
    1.38
     kvalitet
    1.37
    Activations Density 0.016%

    No Known Activations