© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25780
    Prev
    Next
    INDEX
    Explanations

    US election or political figures

    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
    ׇ
    -1.98
     there
    -1.70
    There
    -1.42
     печени
    -1.33
     There
    -1.29
    there
    -1.27
    ἵ
    -1.19
     mães
    -1.19
     their
    -1.18
     to
    -1.17
    POSITIVE LOGITS
    ִּ
    1.55
    ּוֹ
    1.55
     navires
    1.46
    ଷ
    1.38
    dding
    1.36
     reaction
    1.33
    elegante
    1.32
    opie
    1.30
    ַּ
    1.30
    ebly
    1.30
    Activations Density 0.094%

    No Known Activations