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-65K
    4. 3188
    Prev
    Next
    INDEX
    Explanations

    gaze and haze

    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_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
    би
    0.92
     মানুষের
    0.75
     tentang
    0.75
    ো
    0.73
    nię
    0.73
     pudieron
    0.73
     પ
    0.72
    비
    0.72
     papp
    0.71
    क्रामक
    0.71
    POSITIVE LOGITS
    AsString
    0.81
    Inbox
    0.77
     خاصة
    0.76
    chmod
    0.75
    MVP
    0.75
    当然
    0.73
    OfThe
    0.72
     Protein
    0.72
     esperado
    0.70
     overland
    0.70
    Activations Density 0.001%

    No Known Activations