© 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. 2437
    Prev
    Next
    INDEX
    Explanations

    scripts, extensions, plugins, links

    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
    <0xE2>
    1.92
     dé
    1.70
    <i>
    1.64
    1.55
    a
    1.52
    ത്തേ
    1.50
     dél
    1.48
     réfé
    1.41
     gráfica
    1.40
    3
    1.40
    POSITIVE LOGITS
     fanatics
    2.67
     youngsters
    2.59
     당신
    2.54
     entertainers
    2.50
     forefathers
    2.49
     proprietors
    2.47
     desires
    2.46
     civilizations
    2.43
     establishments
    2.43
     delicacies
    2.42
    Activations Density 1.335%

    No Known Activations