© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1607
    Prev
    Next
    INDEX
    Explanations

    assignment in conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    のかもしれません
    -0.78
     Hearst
    -0.74
    えると
    -0.73
    因为它
    -0.72
    に参加
    -0.71
    ➭
    -0.71
    因为他
    -0.70
     Increased
    -0.70
     Rotten
    -0.70
     Anchorage
    -0.70
    POSITIVE LOGITS
    AndSet
    0.84
    illiard
    0.83
     assigns
    0.80
    esterno
    0.80
    ',\
    0.80
    (!(
    0.79
     огур
    0.77
    OVERN
    0.76
    ⓞ
    0.73
     valable
    0.73
    Activations Density 0.015%

    No Known Activations