© 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. 7-GEMMASCOPE-2-RES-16K
    7. 301
    Prev
    Next
    INDEX
    Explanations

    numbers and delimiters

    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_7_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
    minimum
    1.34
    و
    1.31
    motiv
    1.27
    고
    1.26
    ადა
    1.26
    وام
    1.22
     optimal
    1.22
     motiv
    1.22
    larger
    1.19
    sset
    1.18
    POSITIVE LOGITS
     piezas
    1.66
    áver
    1.61
     Janeiro
    1.60
    膩
    1.60
    ízo
    1.59
    ometro
    1.59
    izado
    1.57
    überkü
    1.56
     anunciou
    1.54
    ത്തിക
    1.53
    Activations Density 1.260%

    No Known Activations