© 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. 91304
    Prev
    Next
    INDEX
    Explanations

    actual, real

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

    intrinsic value

    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
     เบ
    0.45
     あ
    0.44
     Statistical
    0.42
     déjà
    0.41
     gep
    0.41
     Уже
    0.41
     contraindicated
    0.41
     ARN
    0.41
     footnotes
    0.40
    愠
    0.40
    POSITIVE LOGITS
     genuine
    0.93
    genuine
    0.92
     genuinely
    0.91
    實際
    0.86
    实际
    0.84
     actual
    0.84
    Genuine
    0.83
    真实的
    0.82
    actual
    0.81
    真正的
    0.80
    Activations Density 0.282%

    No Known Activations