© 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. 22-GEMMASCOPE-2-RES-16K
    7. 9378
    Prev
    Next
    INDEX
    Explanations

    be convening or scheduling

    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_22_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
    쭌
    0.91
     поступи
    0.83
     হঠাৎ
    0.81
    اده
    0.80
    弱
    0.75
    slip
    0.75
    ダメ
    0.74
    单一
    0.74
    炔
    0.72
     अल्पसंख्यक
    0.72
    POSITIVE LOGITS
     enjoined
    1.18
     injunction
    1.13
     ransom
    1.13
     boycot
    1.10
     injunctive
    1.03
     enjoin
    1.00
     compensatory
    1.00
     मुआव
    0.98
     court
    0.98
     reimbursed
    0.97
    Activations Density 0.185%

    No Known Activations