© 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
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 14141
    Prev
    Next
    INDEX
    Explanations

    synth pad sound

    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
    ="#!"
    2.61
    рур
    2.36
    便宜
    2.34
    ldots
    2.32
    matory
    2.31
    աք
    2.31
    וכ
    2.24
     তোলেন
    2.24
    רום
    2.24
    vá
    2.24
    POSITIVE LOGITS
    ivní
    2.93
    ové
    2.85
    ད
    2.71
    ುತ್ತದೆ
    2.67
    esu
    2.64
    owy
    2.61
    मंडल
    2.58
    িক
    2.57
    es
    2.55
     fric
    2.51
    Activations Density 0.010%

    No Known Activations