© 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. 34041
    Prev
    Next
    INDEX
    Explanations

    midpoints of quadrilaterals and triangles

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

    geometric intersections and points

    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
    一丝
    0.46
    と同
    0.45
    Temperatura
    0.45
    蓓
    0.45
     측정
    0.45
     അള
    0.44
    ორის
    0.44
    顼
    0.44
    ギュラー
    0.44
    calup
    0.43
    POSITIVE LOGITS
     dialysis
    0.52
     VP
    0.50
     giao
    0.47
     perturbations
    0.47
     radiotherapy
    0.47
     Navi
    0.46
     scint
    0.46
     Ka
    0.45
     shutt
    0.45
     eject
    0.44
    Activations Density 0.001%

    No Known Activations