© 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. 184350
    Prev
    Next
    INDEX
    Explanations

    Spain achieved, Institute Team, extensive regulations

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

    option, echoed, submit, resources, canyons

    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
    shop
    0.58
    ter
    0.53
    లో
    0.50
    listing
    0.49
    O
    0.48
    county
    0.47
     cushion
    0.46
    ﻟ
    0.46
    pattern
    0.46
     transferring
    0.46
    POSITIVE LOGITS
     acúst
    0.50
     孔
    0.50
     Bleu
    0.49
     přek
    0.48
    ഡിയ
    0.47
     realizzazione
    0.47
    édié
    0.46
     stylu
    0.46
     Draco
    0.46
     विशेषताओं
    0.46
    Activations Density 0.000%

    No Known Activations