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. 3131
    Prev
    Next
    INDEX
    Explanations

    time or states of being

    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
     क्‍या
    0.72
     বক্তব
    0.72
    퇸
    0.65
    ﻅ
    0.63
     discovers
    0.63
    鳇
    0.63
    枸
    0.62
     môže
    0.62
    。
    0.62
    ٫
    0.62
    POSITIVE LOGITS
     internally
    0.58
     via
    0.55
     internal
    0.54
     estern
    0.53
     around
    0.49
     previously
    0.49
     externally
    0.48
     through
    0.48
     త
    0.47
     external
    0.47
    Activations Density 0.000%

    No Known Activations