© 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. 243545
    Prev
    Next
    INDEX
    Explanations

    wrapping issues; court proceedings

    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
    defeated
    0.42
    package
    0.41
    噂
    0.40
    맛집
    0.39
    NAME
    0.39
     Refugees
    0.39
    ドイツ
    0.39
     INDIA
    0.38
    ahiye
    0.38
    週末
    0.38
    POSITIVE LOGITS
     clad
    0.50
     metaphorical
    0.50
     multiplications
    0.49
     forceful
    0.48
     cones
    0.48
     webbing
    0.48
     tableau
    0.47
     panes
    0.47
    🎠
    0.47
     obstructions
    0.46
    Activations Density 0.003%

    No Known Activations