Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-16K
    4. 48
    Prev
    Next
    INDEX
    Explanations

    electric vehicles and futures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     juga
    0.79
     également
    0.77
    💟
    0.73
     browser
    0.73
     compiler
    0.72
     zu
    0.71
     manufacturer
    0.70
     di
    0.70
    ❣
    0.70
     b
    0.70
    POSITIVE LOGITS
    There
    1.29
    The
    1.24
    They
    1.24
    For
    1.22
    It
    1.22
    That
    1.21
    We
    1.21
    You
    1.21
    But
    1.20
    As
    1.16
    Activations Density 4.233%

    No Known Activations