© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 8779
    Prev
    Next
    INDEX
    Explanations

    Uno, pico, auto, halo, crypto

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_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
    ם
    4.21
    م
    4.20
    ক
    4.05
    m
    4.00
    ところ
    3.98
    ಯಲ್ಲಿ
    3.98
    n
    3.87
    র
    3.78
    น้ำ
    3.72
    may
    3.65
    POSITIVE LOGITS
    pped
    4.03
    ে
    3.97
    ه
    3.78
    ة
    3.67
    ed
    3.65
    o
    3.54
    fficial
    3.21
    ﻗ
    3.04
    ffic
    3.00
    े
    2.97
    Activations Density 0.559%

    No Known Activations