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-3-1B-IT
    3. 17-GEMMASCOPE-2-RES-16K
    4. 2125
    Prev
    Next
    INDEX
    Explanations

    exclamatory punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_17_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
    \_
    1.01
     yada
    0.94
    <unused801>
    0.92
     jeweil
    0.90
    <unused873>
    0.90
    maybe
    0.90
     assh
    0.89
    要么
    0.87
    गेटिव
    0.87
    <unused909>
    0.87
    POSITIVE LOGITS
    !
    2.81
     !
    2.50
    !
    2.09
    !!
    2.04
     !!
    2.03
    !)
    1.98
    !"
    1.97
    !!!
    1.96
    '!
    1.93
    !).
    1.88
    Activations Density 0.292%

    No Known Activations