© 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. 403
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     ל
    1.32
     ש
    1.28
     Во
    1.27
    <unused298>
    1.25
     כ
    1.24
    besiege
    1.22
     צ
    1.22
    wpilibj
    1.22
    <unused340>
    1.22
    <unused725>
    1.21
    POSITIVE LOGITS
    inka
    0.93
    ito
    0.90
    ちゃん
    0.88
    ita
    0.88
    ì
    0.88
     selaku
    0.85
     presidente
    0.84
    ian
    0.84
     portavoz
    0.84
    iana
    0.83
    Activations Density 1.477%

    No Known Activations