© 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. 14260
    Prev
    Next
    INDEX
    Explanations

    NVIDIA RTX graphics cards

    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
    ми
    2.83
    ᐟ
    2.32
    lamp
    2.18
    мі
    2.11
     থাম
    2.08
    தா
    2.06
     gross
    2.06
    pana
    2.04
    pan
    2.04
    gom
    2.03
    POSITIVE LOGITS
     doings
    1.81
    ataan
    1.77
     seniority
    1.74
    beiter
    1.73
    롭
    1.70
    attutto
    1.69
    瑷
    1.69
    𝚢
    1.67
     nourishment
    1.66
    aków
    1.66
    Activations Density 0.052%

    No Known Activations