© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 1448
    Prev
    Next
    INDEX
    Explanations

    break down into parts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_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
    র
    3.18
    toc
    3.15
    t
    3.12
    tos
    3.03
    tay
    3.02
    서
    3.02
    ्य
    2.94
    ת
    2.86
    ल
    2.85
    lare
    2.85
    POSITIVE LOGITS
    맟
    2.61
    ged
    2.53
    ﻯ
    2.46
    irane
    2.39
    Mine
    2.38
    ppling
    2.38
    ী
    2.37
    ERRE
    2.36
    نائ
    2.36
    DA
    2.28
    Activations Density 0.174%

    No Known Activations