© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 12562
    Prev
    Next
    INDEX
    Explanations

    coach followed by name

    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
    </em>
    -1.70
    皤
    -1.70
    跸
    -1.67
     cán
    -1.66
    ;\\
    -1.65
     dwóch
    -1.64
    ,\\
    -1.64
    ῞
    -1.63
     ferocious
    -1.63
    に於
    -1.63
    POSITIVE LOGITS
    If
    2.52
    With
    2.44
    When
    2.42
    This
    2.38
    While
    2.33
    After
    2.31
    Although
    2.30
    The
    2.27
    Since
    2.25
    These
    2.22
    Activations Density 0.005%

    No Known Activations