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. 29-GEMMASCOPE-2-RES-262K
    4. 53229
    Prev
    Next
    INDEX
    Explanations

    up to September 2021

    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_29_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
    ຕໍ່
    0.75
    Jamie
    0.70
    해
    0.69
     protesta
    0.68
     बजाज
    0.68
     Warning
    0.67
     જ
    0.66
     समझौते
    0.66
     மாநக
    0.66
     Flücht
    0.65
    POSITIVE LOGITS
    alk
    0.70
     Ank
    0.62
    quila
    0.62
    abin
    0.61
    倍
    0.59
    芊
    0.59
     qualifications
    0.59
    🅐
    0.58
    𝚋
    0.58
    phia
    0.58
    Activations Density 0.009%

    No Known Activations