© 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. 7-GEMMASCOPE-2-RES-16K
    7. 11313
    Prev
    Next
    INDEX
    Explanations

    writing to files

    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
    ট
    3.35
    𝙣
    2.88
    ن
    2.83
    נה
    2.78
    стви
    2.71
     nbfs
    2.68
    𝙧
    2.68
    砰
    2.66
    디오
    2.65
    ע
    2.64
    POSITIVE LOGITS
    mip
    3.02
    sop
    2.78
    ska
    2.76
    tat
    2.71
    ti
    2.52
    mos
    2.48
    ...+
    2.47
    sulf
    2.43
    spray
    2.42
    此之外
    2.42
    Activations Density 0.034%

    No Known Activations