© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 240154
    Prev
    Next
    INDEX
    Explanations

    transactional or official communication

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Compat
    0.48
    Deborah
    0.46
    مس
    0.45
    سب
    0.45
     기타
    0.45
    нется
    0.44
    무
    0.44
    τητας
    0.44
     الرحمن
    0.43
     Inside
    0.43
    POSITIVE LOGITS
    r
    0.56
    o
    0.52
    br
    0.49
    branch
    0.49
     seascape
    0.48
    bran
    0.47
     streams
    0.46
    bay
    0.46
     exiled
    0.46
     drove
    0.45
    Activations Density 0.000%

    No Known Activations