© 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. 10-GEMMASCOPE-RES-131K
    7. 112748
    Prev
    Next
    INDEX
    Explanations

    skepticism and skeptical

    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
     Mainly
    -2.45
     Hoping
    -2.39
     Such
    -2.30
     Could
    -2.27
     The
    -2.27
     Presumably
    -2.25
     Recently
    -2.23
     be
    -2.23
     Previously
    -2.20
     At
    -2.19
    POSITIVE LOGITS
    0
    2.59
    臯
    2.13
    but
    2.13
    \
    2.09
    et
    2.05
    何度
    1.97
    菒
    1.96
     tne
    1.95
    there
    1.93
    戋
    1.89
    Activations Density 0.003%

    No Known Activations