© 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. 3488
    Prev
    Next
    INDEX
    Explanations

    resolving issues, errors, or conflicts

    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
    স্পষ্ট
    2.67
    ја
    2.65
    燥
    2.62
    উন্ট
    2.62
    icznego
    2.58
    勇敢
    2.52
    ¦
    2.48
    ョ
    2.47
    കൊ
    2.46
    ثل
    2.46
    POSITIVE LOGITS
    𝘪
    3.03
    𝘥
    2.89
    𝘴
    2.84
    MACl
    2.77
    𝘳
    2.74
    ributedString
    2.67
    𝘢
    2.65
    𝘻
    2.55
    t
    2.53
    di
    2.52
    Activations Density 0.125%

    No Known Activations