© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 1099
    Prev
    Next
    INDEX
    Explanations

    negotiation, iPhone, software, API, initial, local

    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
    nya
    9.07
    了
    8.52
    ्स
    6.77
    다고
    6.19
    ness
    5.98
    اً
    5.95
    n
    5.89
    ly
    5.88
    ten
    5.85
    다면
    5.68
    POSITIVE LOGITS
    ٔ
    4.82
    которые
    3.99
    ւ
    3.67
    ptide
    3.45
    autiful
    3.42
    ٴ
    3.33
    utenant
    3.28
    very
    3.26
    javax
    3.17
    źdz
    3.17
    Activations Density 3.369%

    No Known Activations