© 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. 135478
    Prev
    Next
    INDEX
    Explanations

    quantifies, developer insights, solutions, cameras, challenges, timely, string, advertisers

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

    list formatting or instructions

    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
    ri
    0.51
    p
    0.47
    den
    0.45
    ta
    0.45
    ref
    0.44
    pre
    0.43
    ור
    0.43
    shaft
    0.43
    label
    0.43
    רה
    0.42
    POSITIVE LOGITS
     спец
    0.57
    œurs
    0.54
     သူ့
    0.53
     Kaspersky
    0.53
     ସ
    0.52
    စိတ်
    0.52
    зре
    0.51
    実践
    0.51
    ଦ
    0.50
     поезд
    0.50
    Activations Density 0.001%

    No Known Activations