© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-262K
    7. 149044
    Prev
    Next
    INDEX
    Explanations

    acronyms followed by numbers

    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
     başta
    0.80
     @"
    0.74
     👇
    0.73
    ″]
    0.72
     paling
    0.72
    之前的
    0.70
    တို့
    0.69
    ൊക്കെ
    0.68
     ஆகியவற்ற
    0.68
     や
    0.68
    POSITIVE LOGITS
    8
    1.13
    7
    1.08
    9
    1.07
    5
    0.98
    1
    0.98
    6
    0.98
     Series
    0.96
    4
    0.86
    2
    0.84
    ۵
    0.84
    Activations Density 0.014%

    No Known Activations