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. 9-GEMMASCOPE-2-RES-262K
    4. 7301
    Prev
    Next
    INDEX
    Explanations

    Matplotlib

    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_9_width_262k_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
    a
    3.77
    ে
    3.44
    ه
    3.43
    ер
    3.41
    িং
    3.28
    er
    3.27
    aik
    3.21
    e
    3.18
    erent
    3.11
    há
    3.08
    POSITIVE LOGITS
    ting
    4.73
    ty
    3.99
    tttt
    3.90
    to
    3.80
    ৃত্বে
    3.79
    ttt
    3.65
    ীব্র
    3.61
    ta
    3.45
    መሳሳይ
    3.38
    न्त्र
    3.25
    Activations Density 0.729%

    No Known Activations