© 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-3-27B-IT
    5. 53-GEMMASCOPE-2-RES-262K
    7. 66480
    Prev
    Next
    INDEX
    Explanations

    hesitation fillers after punctuation

    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_53_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
     u
    0.62
     um
    0.62
     Hmm
    0.60
     उ
    0.59
     hmm
    0.57
    <0x8C>
    0.56
     umjet
    0.52
     우
    0.52
    hum
    0.51
     উ
    0.50
    POSITIVE LOGITS
     where
    0.43
     yeah
    0.42
     anyone
    0.40
    yeah
    0.39
     var
    0.39
     lem
    0.39
     exc
    0.38
     هل
    0.38
     staggering
    0.38
    ye
    0.38
    Activations Density 0.006%

    No Known Activations