© 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. 15963
    Prev
    Next
    INDEX
    Explanations

    national identity and belonging

    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
    filepath
    -1.28
    ↵↵↵
    -1.27
    """
    -1.23
    $};
    -1.17
    ↵↵↵↵
    -1.16
     foreshadow
    -1.15
    чний
    -1.13
    ↵↵
    -1.12
    ombres
    -1.12
     rakyat
    -1.11
    POSITIVE LOGITS
     identity
    1.59
     two
    1.48
     both
    1.30
     identities
    1.28
     identification
    1.27
     belonging
    1.17
     bolster
    1.16
    знание
    1.13
     three
    1.13
     their
    1.13
    Activations Density 0.023%

    No Known Activations