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. 22-GEMMASCOPE-2-RES-65K
    4. 3324
    Prev
    Next
    INDEX
    Explanations

    physical sensations and feelings

    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
     disastrous
    0.84
    🖕
    0.80
     tekr
    0.79
     สุด
    0.76
     implementations
    0.75
     disasters
    0.75
    աբ
    0.74
     yöntem
    0.74
    🤕
    0.73
    🥝
    0.72
    POSITIVE LOGITS
     feeling
    2.08
     ощущение
    1.92
     palpable
    1.87
    feeling
    1.83
     atmosphere
    1.75
     sensação
    1.72
     Feeling
    1.72
     feel
    1.72
     sensación
    1.70
    Feeling
    1.69
    Activations Density 0.732%

    No Known Activations