© 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
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 9133
    Prev
    Next
    INDEX
    Explanations

    memory allocation

    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_13_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
    िक्रमा
    1.68
     hiểu
    1.49
     %=
    1.47
    רית
    1.46
     Beautiful
    1.46
     querida
    1.45
     Tiến
    1.45
    ⬯
    1.44
     générale
    1.44
    ر
    1.43
    POSITIVE LOGITS
    gels
    1.72
    وتا
    1.68
    zees
    1.59
    globalMap
    1.55
    oz
    1.55
    mathrm
    1.51
    gll
    1.50
    杷
    1.50
    mba
    1.47
    stit
    1.44
    Activations Density 0.001%

    No Known Activations