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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-262K
    4. 52898
    Prev
    Next
    INDEX
    Explanations

    2 followed by 5

    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_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
    লেট
    0.72
    柑
    0.66
    wiąz
    0.66
     Tribes
    0.66
    Stim
    0.65
     Stimulation
    0.65
     нико
    0.65
    けて
    0.65
     Kultur
    0.63
    ivil
    0.63
    POSITIVE LOGITS
    वता
    0.68
     nerve
    0.64
    皁
    0.64
     PCP
    0.60
    甶
    0.60
     παιδιά
    0.60
     হেঁ
    0.59
    ങ്ങളുടെ
    0.59
    amura
    0.59
    FileOutputStream
    0.58
    Activations Density 0.005%

    No Known Activations