© 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. 83607
    Prev
    Next
    INDEX
    Explanations

    claim, etching, shadow, true

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

    shadows stretching

    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
    เส
    0.46
    蓯
    0.46
    bier
    0.44
    කට
    0.43
     morate
    0.41
    います
    0.40
    ONES
    0.40
     크게
    0.40
     пона
    0.40
    առ
    0.39
    POSITIVE LOGITS
    क्षा
    0.48
     विधान
    0.47
     lineages
    0.47
    諗
    0.47
     वेगवेगळ्या
    0.46
    pegno
    0.46
    紥
    0.46
    jectory
    0.45
     lauded
    0.45
     मायणी
    0.45
    Activations Density 0.000%

    No Known Activations