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-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 9270
    Prev
    Next
    INDEX
    Explanations

    French, Finnish, Roman, Ukraine

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
    強度
    0.48
     переста
    0.47
    ме
    0.47
     ಎ
    0.45
    好多
    0.45
    Fore
    0.44
     ઇ
    0.44
    齜
    0.44
     untersucht
    0.43
     л
    0.43
    POSITIVE LOGITS
    ibilities
    0.50
    anne
    0.50
    alim
    0.49
    link
    0.47
    foot
    0.47
    ivali
    0.46
    ive
    0.45
    sthe
    0.45
    maids
    0.45
    aid
    0.44
    Activations Density 0.001%

    No Known Activations