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-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 195849
    Prev
    Next
    INDEX
    Explanations

    numbers, quantities, limits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_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
     Volt
    0.42
     <=
    0.41
     [['
    0.40
     Zeit
    0.39
     Wonders
    0.37
     Finest
    0.36
     ಮಂಗಳ
    0.36
     Complexes
    0.36
     ഇട
    0.35
    챌
    0.35
    POSITIVE LOGITS
     hundred
    0.52
    thousand
    0.52
     hundert
    0.51
     thousand
    0.47
    ousand
    0.46
    >∞</
    0.46
     હજાર
    0.46
     беско
    0.45
    Hundred
    0.45
     १००
    0.44
    Activations Density 0.009%

    No Known Activations