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. 47036
    Prev
    Next
    INDEX
    Explanations

    things you can

    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
     perj
    1.10
    的に
    1.09
     leaps
    1.06
    ะ
    1.03
    pä
    1.01
     telefonu
    1.01
    म
    1.01
    Ін
    1.00
    ბ
    0.98
    Lovely
    0.98
    POSITIVE LOGITS
     قص
    1.08
     이상
    1.07
    readdir
    1.07
    栩
    1.04
    ir
    1.02
     compre
    1.01
    izontal
    1.00
     ocurren
    0.98
     моз
    0.98
     IRI
    0.96
    Activations Density 0.003%

    No Known Activations