© 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. 179277
    Prev
    Next
    INDEX
    Explanations

    watch monitoring

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

    Status Checks, Classics, foundational

    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
    at
    0.61
    ad
    0.61
    al
    0.60
    in
    0.55
    ar
    0.52
    n
    0.51
    tal
    0.49
     gene
    0.49
    u
    0.48
     lambda
    0.48
    POSITIVE LOGITS
    кансер
    0.52
    ків
    0.50
    觫
    0.48
    ाइवेट
    0.47
    ђу
    0.46
    वतात
    0.46
    ologischen
    0.45
     Communism
    0.45
    をも
    0.45
    の一つ
    0.45
    Activations Density 0.000%

    No Known Activations