© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 113672
    Prev
    Next
    INDEX
    Explanations

    Avoid: syllables, source, scratch, slang, whether

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itinéraires
    0.52
     carénés
    0.52
     teşekkür
    0.45
     Aliens
    0.45
    碉
    0.45
     Inspir
    0.45
     trời
    0.44
     scooters
    0.44
     terrific
    0.44
     takePhotoButton
    0.44
    POSITIVE LOGITS
    ﻼ
    0.54
    escent
    0.48
    vek
    0.47
    and
    0.44
    agnet
    0.44
     expectancy
    0.43
    can
    0.43
    cium
    0.43
    [
    0.43
    ული
    0.42
    Activations Density 0.005%

    No Known Activations