Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 17-GEMMASCOPE-2-RES-65K
    4. 1994
    Prev
    Next
    INDEX
    Explanations

    also, too

    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
    :
    0.79
    iz
    0.75
    (
    0.74
    id
    0.70
    i
    0.70
    so
    0.70
    Therefore
    0.69
     therefore
    0.67
    .
    0.67
     which
    0.67
    POSITIVE LOGITS
     También
    1.25
     Ayrıca
    1.22
     Also
    1.19
     también
    1.18
     tambien
    1.18
     també
    1.10
     또한
    1.09
     cũng
    1.07
     außerdem
    1.06
     myös
    1.04
    Activations Density 1.063%

    No Known Activations