© 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. 7-GEMMASCOPE-2-RES-16K
    7. 1986
    Prev
    Next
    INDEX
    Explanations

    HTML table headers and paragraphs

    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
    △
    1.49
    ೂರ್ವ
    1.48
    KindOfClass
    1.46
    蕖
    1.45
     годах
    1.39
     씨
    1.39
     jih
    1.38
     nadal
    1.36
    無法
    1.36
     血
    1.35
    POSITIVE LOGITS
    י
    2.40
    er
    2.36
    ו
    2.35
    ه
    2.25
    o
    2.23
    a
    2.19
    y
    2.18
    an
    2.18
    ي
    2.08
    т
    2.07
    Activations Density 0.017%

    No Known Activations