© 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. 14211
    Prev
    Next
    INDEX
    Explanations

    asking for vibe examples

    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
    柺
    1.78
     では
    1.74
     asociada
    1.73
     encargado
    1.72
     encabez
    1.72
     जोरदार
    1.70
    obiettivo
    1.70
     correspondiente
    1.70
     ссылку
    1.68
     hỗ
    1.67
    POSITIVE LOGITS
    b
    1.37
    OU
    1.36
     truths
    1.32
    things
    1.31
    sk
    1.27
    st
    1.25
     etc
    1.25
     ..
    1.24
    mov
    1.24
    sn
    1.24
    Activations Density 0.061%

    No Known Activations