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. 22-GEMMASCOPE-2-RES-16K
    4. 3743
    Prev
    Next
    INDEX
    Explanations

    exclamations and emphatic punctuation

    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_22_width_16k_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
    en
    2.69
    ت
    2.23
    ン
    1.93
    те
    1.92
    ే
    1.75
    ená
    1.67
    ené
    1.67
    ה
    1.66
    enol
    1.63
    ن
    1.61
    POSITIVE LOGITS
    ?!?
    2.99
    ?!?!
    2.59
    !!!!!!
    2.00
    !!!!!!!
    1.98
    !!!!!!!!
    1.90
     exclaimed
    1.86
    !!!!!!!!!!!!!!!!
    1.69
    '"
    1.64
    да
    1.59
    ﻲ
    1.58
    Activations Density 0.169%

    No Known Activations