© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 10267
    Prev
    Next
    INDEX
    Explanations

    typescript and javascript code

    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
    闊
    1.19
    inally
    1.16
    PickerController
    1.14
    angaroo
    1.10
    pleasant
    1.09
     prothorax
    1.07
    lng
    1.06
    娥
    1.06
     móc
    1.06
     handy
    1.06
    POSITIVE LOGITS
    !!!!!
    1.18
    WAY
    1.12
    (
    1.08
    ibernate
    1.08
     हराकर
    1.08
    GING
    1.06
    ysis
    1.05
    eek
    1.04
    тесь
    1.02
    smt
    1.02
    Activations Density 0.079%

    No Known Activations