© 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. 14314
    Prev
    Next
    INDEX
    Explanations

    serial killer, serial numbers, serial entrepreneur

    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
    훗
    3.09
    seit
    2.90
    elf
    2.45
    ľa
    2.45
    handleChange
    2.39
    팥
    2.37
    klik
    2.33
    𝚎
    2.29
    대학
    2.29
    चाप
    2.28
    POSITIVE LOGITS
     '/',
    2.86
    ojas
    2.85
    ────────────────
    2.85
     '-',
    2.69
     gifted
    2.65
    路上
    2.65
    繹
    2.63
    weapp
    2.60
     emanc
    2.60
     liberated
    2.57
    Activations Density 0.002%

    No Known Activations