© 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. 13-GEMMASCOPE-2-RES-16K
    7. 1157
    Prev
    Next
    INDEX
    Explanations

    resources and support

    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_13_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
    จำ
    1.13
    จ
    1.12
    เผ
    1.09
     Arm
    1.09
    เส
    1.04
    Sher
    1.02
    личи
    1.02
    คำ
    1.02
    Band
    1.00
    Ку
    0.99
    POSITIVE LOGITS
    <unused309>
    1.69
    <unused307>
    1.65
    <unused1896>
    1.64
    <unused350>
    1.53
    <unused1745>
    1.52
    <unused397>
    1.52
     isnt
    1.50
    <unused599>
    1.50
     你
    1.49
    <unused1771>
    1.49
    Activations Density 2.794%

    No Known Activations