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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-65K
    4. 1290
    Prev
    Next
    INDEX
    Explanations

    expl/tabular/larva

    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_29_width_65k_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
     software
    0.67
     unconscious
    0.66
    敚
    0.66
     denomination
    0.66
    ደም
    0.66
    obin
    0.65
    ektor
    0.65
    ர்களும்
    0.65
     diode
    0.64
    RY
    0.64
    POSITIVE LOGITS
     কৌশল
    0.68
     alebo
    0.67
    tabular
    0.65
    plant
    0.65
    expl
    0.62
     larva
    0.62
    tab
    0.61
    <eos>
    0.61
     तैयारियों
    0.60
     Или
    0.60
    Activations Density 0.023%

    No Known Activations