© 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. 14492
    Prev
    Next
    INDEX
    Explanations

    come: in, from, to, home

    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
    occhi
    2.31
    ags
    2.28
    acci
    2.24
    ീയ
    2.24
    rivial
    2.17
    $\
    2.15
     brill
    2.15
    ș
    2.12
    inburgh
    2.08
     thrown
    2.08
    POSITIVE LOGITS
    منا
    2.62
    偐
    2.48
    ▶
    2.41
    儩
    2.41
     पर्या
    2.40
    పాద
    2.40
    娌
    2.40
    го
    2.32
    Composite
    2.28
    رځ
    2.27
    Activations Density 0.013%

    No Known Activations