© 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. 1948
    Prev
    Next
    INDEX
    Explanations

    point out that

    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
     allusion
    3.06
     inductance
    3.04
    ו
    2.90
     lParam
    2.77
    oise
    2.75
    emphasis
    2.75
    ividual
    2.63
    м
    2.61
    на
    2.57
    ルメ
    2.55
    POSITIVE LOGITS
    leri
    2.09
    ജീവ
    2.02
     dàng
    1.96
    פתח
    1.95
    তাবাদী
    1.89
    יית
    1.87
    operatorname
    1.86
    <0x0C>
    1.85
    ací
    1.84
    dT
    1.83
    Activations Density 0.001%

    No Known Activations