© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 65669
    Prev
    Next
    INDEX
    Explanations

    have a / an / all / enough

    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
     rých
    -1.47
     ktoś
    -1.33
     všetky
    -1.29
    enseignements
    -1.23
     ľah
    -1.22
     budete
    -1.22
     weren
    -1.20
    ffl
    -1.20
     of
    -1.18
     would
    -1.18
    POSITIVE LOGITS
     a
    1.31
     voller
    1.19
    rdoba
    1.19
    內的
    1.16
    >
    1.13
     jätte
    1.13
    穣
    1.13
     its
    1.10
     any
    1.09
    内部
    1.09
    Activations Density 0.190%

    No Known Activations