© 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. 147973
    Prev
    Next
    INDEX
    Explanations

    create or grant

    np_acts-logits-general · gemini-2.5-flash-lite

    roses are red

    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
     daí
    0.50
    ጶ
    0.49
     cancelling
    0.48
     tı
    0.46
     tuto
    0.46
     celu
    0.46
     steric
    0.46
    ونة
    0.46
     cancellation
    0.45
     loin
    0.45
    POSITIVE LOGITS
    arker
    0.52
    inhua
    0.52
    ub
    0.47
    ushima
    0.47
    抗
    0.46
    lication
    0.43
    、
    0.43
    urses
    0.41
    aya
    0.41
     Film
    0.41
    Activations Density 0.000%

    No Known Activations