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. 556
    Prev
    Next
    INDEX
    Explanations

    degree of variation

    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
    apus
    0.72
    ИН
    0.67
    罢了
    0.66
    khart
    0.64
    ගත්
    0.64
    aphys
    0.64
    lawful
    0.62
    婼
    0.62
    িন্দা
    0.60
    ជូន
    0.60
    POSITIVE LOGITS
     significantly
    3.91
     drastically
    3.81
     dramatically
    3.81
     greatly
    3.65
     considerably
    3.57
     substantially
    3.37
     vastly
    3.24
     tremendously
    3.23
     markedly
    3.22
     enormously
    3.20
    Activations Density 0.663%

    No Known Activations