© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 2864
    Prev
    Next
    INDEX
    Explanations

    brute-force attacks

    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
    o
    2.72
    es
    2.49
    u
    2.30
    a
    2.30
    an
    2.25
    ו
    2.24
    ه
    2.23
    e
    2.22
    ר
    2.13
    oč
    1.98
    POSITIVE LOGITS
    。.
    2.46
    𝚢
    2.37
    ꯣ
    2.37
    𝚔
    2.29
    𠃍
    2.27
    。"
    2.27
    𝕝
    2.25
    ᒍ
    2.23
    பீ
    2.22
    ⱼ
    2.22
    Activations Density 0.078%

    No Known Activations