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-262K
    4. 53102
    Prev
    Next
    INDEX
    Explanations

    washington post and seattle times

    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
     DC
    1.28
    DC
    1.17
     TDC
    0.98
     DCs
    0.97
     D
    0.96
     DCS
    0.95
     DCP
    0.91
    NYC
    0.88
    DCs
    0.87
    dc
    0.86
    POSITIVE LOGITS
     crypt
    0.62
    ados
    0.60
     заре
    0.57
     position
    0.56
    iero
    0.56
    ADOS
    0.56
    amento
    0.55
    কালীন
    0.55
     pozycji
    0.54
    ै
    0.53
    Activations Density 0.000%

    No Known Activations