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. 47080
    Prev
    Next
    INDEX
    Explanations

    Corriente Continua (CC), participles

    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
    蓣
    1.27
    symplectic
    1.26
     auxin
    1.26
     interrupt
    1.21
     corticoster
    1.16
     pavatt
    1.16
     végétation
    1.16
     aquifer
    1.15
     ബ്രി
    1.13
    popUp
    1.13
    POSITIVE LOGITS
    ua
    1.13
    Russia
    1.10
    i
    1.09
    in
    1.06
    Belgium
    1.02
     India
    1.01
    all
    1.00
    at
    1.00
    Spain
    0.99
     Russia
    0.99
    Activations Density 0.000%

    No Known Activations