© 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. 22-GEMMASCOPE-RES-131K
    7. 36316
    Prev
    Next
    INDEX
    Explanations

    foreign language references to people

    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
     from
    -1.27
     also
    -1.20
     arbeiten
    -1.16
     lernen
    -1.13
     our
    -1.12
    нт
    -1.10
     who
    -1.08
     edil
    -1.08
     by
    -1.08
     you
    -1.08
    POSITIVE LOGITS
    这般
    1.20
     ícone
    1.20
     obstin
    1.18
    を見せて
    1.14
     isolamento
    1.14
     Ejemplo
    1.13
     jardim
    1.11
     banheiro
    1.10
     casamento
    1.10
     immor
    1.09
    Activations Density 0.058%

    No Known Activations