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. 47276
    Prev
    Next
    INDEX
    Explanations

    proposal and strategy generation

    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
    i
    1.44
    u
    1.27
    e
    1.22
    am
    1.22
    iin
    1.22
    os
    1.21
    te
    1.17
    c
    1.17
    em
    1.12
    de
    1.10
    POSITIVE LOGITS
     burdensome
    1.45
     bittern
    1.44
     gayi
    1.40
    idescent
    1.37
     недель
    1.36
     agrícola
    1.32
    каде
    1.28
    Види
    1.28
     hauled
    1.28
     detained
    1.27
    Activations Density 0.001%

    No Known Activations