© 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. 157931
    Prev
    Next
    INDEX
    Explanations

    opposed to rematch distances

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

    within or without

    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
    स्यों
    0.49
     haszn
    0.47
     Officers
    0.45
    仴
    0.44
    舊
    0.42
     entw
    0.42
    nten
    0.41
    enheim
    0.41
    manirrahim
    0.41
     Yatha
    0.41
    POSITIVE LOGITS
     spotted
    0.54
     decreases
    0.47
     Doubles
    0.46
     doub
    0.46
     doubles
    0.45
    നാണ്
    0.45
     Spotted
    0.44
     slows
    0.43
    ﻪ
    0.43
     selon
    0.43
    Activations Density 0.000%

    No Known Activations