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. 17-GEMMASCOPE-2-RES-65K
    4. 47031
    Prev
    Next
    INDEX
    Explanations

    same measure of length

    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_17_width_65k_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
    ت
    1.46
     Paryayvachi
    1.40
     الكهربائيه
    1.34
    л
    1.26
    sembling
    1.26
    enemies
    1.26
     unrivalled
    1.26
     तानाशाह
    1.25
     biennial
    1.25
    ताज
    1.24
    POSITIVE LOGITS
    观点
    0.94
    いる
    0.90
     halen
    0.87
    றை
    0.84
     bolso
    0.83
     informacija
    0.81
    菀
    0.81
    льт
    0.80
    vspace
    0.80
    しさ
    0.80
    Activations Density 0.000%

    No Known Activations