© 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. 4302
    Prev
    Next
    INDEX
    Explanations

    marry Mariana

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

    preceded by 'max', 'min', 'size', 'diameter', 'view', 'appendChild', 'name', 'empty'

    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
    战争
    0.39
    𝔯
    0.38
    Kaynak
    0.38
    ร
    0.38
    Projekt
    0.36
    戦争
    0.36
     אטאטורק
    0.35
     ஐந்து
    0.35
    赧
    0.35
     colère
    0.35
    POSITIVE LOGITS
    ↵
    0.48
     (
    0.46
    ’
    0.42
     to
    0.41
     by
    0.40
    .
    0.39
    /
    0.39
     while
    0.38
    ↵↵
    0.38
     using
    0.37
    Activations Density 0.450%

    No Known Activations