© 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. 8816
    Prev
    Next
    INDEX
    Explanations

    taking a position

    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
    otherwise
    -1.41
    Aquí
    -1.37
    since
    -1.37
    zins
    -1.33
    的眼神
    -1.27
    🕗
    -1.26
    cisive
    -1.26
     juſ
    -1.25
     segítség
    -1.25
     พื้น
    -1.24
    POSITIVE LOGITS
     any
    2.06
     or
    1.38
     because
    1.33
    任何
    1.31
     then
    1.29
     but
    1.23
     and
    1.22
     went
    1.16
    However
    1.13
    actéristiques
    1.13
    Activations Density 0.117%

    No Known Activations