Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-262K
    4. 7449
    Prev
    Next
    INDEX
    Explanations

    hesitation and thinking sounds

    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_9_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
    +{\
    2.38
    Ĝ
    2.29
    
    2.28
    larni
    2.20
     către
    2.18
    ită
    2.17
    owego
    2.16
    giphy
    2.16
    ➋
    2.16
     محض
    2.15
    POSITIVE LOGITS
    }-
    2.22
    ்
    2.11
     Ventilation
    1.92
    ोग
    1.87
     Hedgehog
    1.82
     люд
    1.82
    🤔
    1.81
    fw
    1.79
     typo
    1.74
    躇
    1.74
    Activations Density 0.029%

    No Known Activations