© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 4900
    Prev
    Next
    INDEX
    Explanations

    right here, right now

    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
    unlink
    2.22
    uglify
    2.13
    ﺛ
    2.12
    ﮄ
    2.11
    ث
    2.08
     behold
    1.95
    ویزی
    1.93
    reh
    1.89
    вча
    1.88
    orkel
    1.87
    POSITIVE LOGITS
    eous
    2.92
    onaut
    2.66
    leftharpoons
    2.63
    鵠
    2.59
    ައް
    2.40
    gång
    2.40
     \"
    2.37
    ులు
    2.36
    िकल्स
    2.36
    \|
    2.34
    Activations Density 0.333%

    No Known Activations