© 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-65K
    7. 572
    Prev
    Next
    INDEX
    Explanations

    even followed by contrast

    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_65k_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
    tab
    1.76
    ệp
    1.74
    addProduct
    1.72
    t
    1.70
    orn
    1.69
    toire
    1.69
    ervi
    1.64
    ervice
    1.64
    ataire
    1.63
    dé
    1.62
    POSITIVE LOGITS
    詭
    1.85
     worse
    1.80
    気が
    1.79
     recog
    1.77
    ಣೆ
    1.77
    िणी
    1.72
    िक
    1.72
    োডে
    1.72
    िके
    1.72
    ಾಗಲೇ
    1.72
    Activations Density 0.130%

    No Known Activations