© 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. 1711
    Prev
    Next
    INDEX
    Explanations

    my followed by identifiers

    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
    s
    2.78
    eb
    2.58
    ्ज
    2.49
    tre
    2.34
    ่วม
    2.12
    t
    2.11
    ات
    2.09
    ted
    2.08
    eks
    2.07
    ebel
    1.97
    POSITIVE LOGITS
    riad
    2.88
    ये
    2.74
    ‌ای
    2.71
    anmar
    2.65
    plier
    2.53
    𝑮
    2.51
    нков
    2.50
    𝒈
    2.46
    เสีย
    2.45
    యా
    2.45
    Activations Density 0.212%

    No Known Activations