© 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. 22-GEMMASCOPE-RES-131K
    7. 39054
    Prev
    Next
    INDEX
    Explanations

    personal names and pronouns

    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_22/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
     our
    -1.36
     those
    -1.26
     there
    -1.20
     we
    -1.18
     ihnen
    -1.13
     that
    -1.12
     мы
    -1.12
     these
    -1.11
     what
    -1.10
     allí
    -1.10
    POSITIVE LOGITS
     he
    1.79
     him
    1.61
     hän
    1.46
     she
    1.38
     hemel
    1.27
    ToProps
    1.21
    fieldId
    1.19
     данного
    1.18
     exacte
    1.13
    eens
    1.12
    Activations Density 0.107%

    No Known Activations