© 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. 228317
    Prev
    Next
    INDEX
    Explanations

    message, behavior, Twitter, look, smart

    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
     اسلح
    0.48
    呔
    0.45
    ylül
    0.43
    eyn
    0.42
    klasse
    0.42
    arist
    0.41
     ugyan
    0.40
     silah
    0.40
    ļu
    0.40
     மன்ன
    0.40
    POSITIVE LOGITS
    ATION
    0.56
    ウ
    0.50
     cat
    0.49
    Query
    0.48
     ecol
    0.48
     complicate
    0.48
    ON
    0.48
    UATION
    0.46
     환경
    0.46
     revolve
    0.46
    Activations Density 0.000%

    No Known Activations