© 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. 134231
    Prev
    Next
    INDEX
    Explanations

    foreign characters

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

    always double-check review

    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
    ch
    0.47
     Obec
    0.46
    2
    0.45
     transport
    0.43
     metros
    0.42
     kitchens
    0.41
     an
    0.41
    zal
    0.41
     syg
    0.41
    of
    0.40
    POSITIVE LOGITS
     آثار
    0.51
    ラリー
    0.48
    Ժ
    0.47
     ταιν
    0.47
     స్క
    0.46
    રૂ
    0.46
     слабы
    0.46
    JD
    0.44
    Aile
    0.44
     अधू
    0.44
    Activations Density 0.001%

    No Known Activations