© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-4B-IT
    3. 17-GEMMASCOPE-2-RES-16K
    4. 3539
    Prev
    Next
    INDEX
    Explanations

    numbers with units

    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_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
    년대
    0.77
    न
    0.71
    Precio
    0.68
     বেশী
    0.68
    Tuy
    0.68
     Atelier
    0.66
    躇
    0.65
     रवाना
    0.65
    peso
    0.65
     Trabajo
    0.65
    POSITIVE LOGITS
    an
    0.76
    el
    0.70
     lobes
    0.66
     vul
    0.65
    inology
    0.65
    бір
    0.64
    
    0.63
    evich
    0.63
     bona
    0.62
    ecc
    0.62
    Activations Density 0.142%

    No Known Activations