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. 29-GEMMASCOPE-2-RES-65K
    4. 5615
    Prev
    Next
    INDEX
    Explanations

    substance abuse andfile not founderror

    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_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
    S
    0.91
     Pans
    0.77
    Sel
    0.77
     S
    0.77
    Z
    0.75
    Pan
    0.74
     Sel
    0.74
     Patt
    0.72
    P
    0.72
     pant
    0.71
    POSITIVE LOGITS
     Ма
    0.76
     مار
    0.74
     마
    0.72
     Мар
    0.71
     MAR
    0.70
    Ма
    0.70
     ਮ
    0.69
    马克
    0.68
     МА
    0.67
    마
    0.67
    Activations Density 0.126%

    No Known Activations