© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 187352
    Prev
    Next
    INDEX
    Explanations

    mcg drug dosage

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

    compiler technology

    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
     아트
    0.55
    landish
    0.52
     ባ
    0.49
     लाइक
    0.48
     splatter
    0.46
     नेट
    0.45
    FindingsResponse
    0.44
     sparsebundle
    0.44
    SwapChain
    0.43
     তবুও
    0.43
    POSITIVE LOGITS
    I
    0.67
    x
    0.60
    ي
    0.59
    ü
    0.56
    ک
    0.55
    A
    0.54
    هر
    0.52
    O
    0.51
    U
    0.51
    У
    0.51
    Activations Density 0.000%

    No Known Activations