© 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. 963
    Prev
    Next
    INDEX
    Explanations

    grateful for

    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
     trialComponents
    1.85
    ombang
    1.72
    erical
    1.69
    रिमेंट
    1.66
    <unused252>
    1.66
     khawatir
    1.66
    imat
    1.66
    保険
    1.66
    ຂໍ້ມ
    1.65
    <unused522>
    1.62
    POSITIVE LOGITS
    𝒶
    1.32
    𝑎
    1.23
    ει
    1.18
    an
    1.11
     අව
    1.07
     ‘
    1.07
     getHeight
    1.06
     එහි
    1.01
     terrific
    1.00
     constant
    1.00
    Activations Density 0.001%

    No Known Activations