© 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. 14284
    Prev
    Next
    INDEX
    Explanations

    assigning nicknames followed by quotes

    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
    ra
    3.18
    鹃
    3.08
    rt
    3.04
    larak
    2.85
    ga
    2.84
    ertas
    2.78
    ค์
    2.78
    ゅう
    2.74
    关节
    2.73
    ই
    2.68
    POSITIVE LOGITS
    ลำ
    2.38
    кономи
    2.24
    it
    2.18
    hardening
    2.17
    e
    2.15
     tester
    2.15
    eck
    2.12
    amask
    2.10
    ાન
    2.07
    𝙤
    2.05
    Activations Density 0.003%

    No Known Activations