© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 5434
    Prev
    Next
    INDEX
    Explanations

    risk and its context

    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_13_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
    ্রেট
    3.02
    ﻓ
    2.91
     '/')
    2.88
    愀
    2.68
    ﻑ
    2.65
    sampler
    2.59
    ्रेट
    2.54
    𝗰
    2.53
    𝗬
    2.51
    𝗛
    2.51
    POSITIVE LOGITS
    ming
    3.79
    mmm
    3.41
    ্ভব
    3.30
    ilitary
    3.22
    ป์
    3.18
    etric
    3.13
    ्युनिटी
    3.09
    mit
    3.00
    mrow
    2.99
    mmmm
    2.99
    Activations Density 2.533%

    No Known Activations