© 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. 74503
    Prev
    Next
    INDEX
    Explanations

    describing degrees or states

    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
     -
    -1.59
    <b>
    -1.53
    <i>
    -1.48
    *
    -1.42
     its
    -1.41
    V
    -1.29
    Its
    -1.29
    (
    -1.28
    <
    -1.27
    ворачи
    -1.26
    POSITIVE LOGITS
     decorados
    1.66
    ₁,
    1.52
     heilig
    1.50
     spannend
    1.47
     gese
    1.46
     nimmer
    1.45
    '],'
    1.45
     verhind
    1.45
    各样的
    1.43
     keindahan
    1.40
    Activations Density 0.385%

    No Known Activations