© 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. 548
    Prev
    Next
    INDEX
    Explanations

    describing capabilities and operations

    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
     of
    0.85
     I
    0.81
     (
    0.75
     Un
    0.73
     none
    0.72
    0.70
     PD
    0.69
     kind
    0.68
    ness
    0.68
     unknown
    0.67
    POSITIVE LOGITS
    <unused2223>
    1.23
     menjalani
    1.21
    Benzoimidazole
    1.21
    Methylsulfanyl
    1.19
    <unused2217>
    1.16
    羧
    1.16
     abbia
    1.15
    juje
    1.13
    杣
    1.11
     समुद्रा
    1.09
    Activations Density 0.481%

    No Known Activations