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. 2400
    Prev
    Next
    INDEX
    Explanations

    interjections and emoticons

    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
    <unused2197>
    0.73
     maxSize
    0.72
     Forestry
    0.71
     keeping
    0.70
    <unused2173>
    0.70
     great
    0.70
     পাট
    0.70
     quite
    0.70
     Considerable
    0.69
     certainly
    0.69
    POSITIVE LOGITS
    Ha
    1.06
     Sigh
    0.93
     Ha
    0.92
    Oh
    0.92
     ha
    0.90
    ♡
    0.90
     O
    0.89
     
    0.86
     :/
    0.85
    OH
    0.85
    Activations Density 0.226%

    No Known Activations