© 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
    3. Gemma-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 356
    Prev
    Next
    INDEX
    Explanations

    to convey

    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
    Насе
    0.43
    В
    0.41
    Ва
    0.41
     Biblioteca
    0.40
     Autodesk
    0.39
    Таким
    0.38
    โครงการ
    0.38
     didactic
    0.38
    ዐይን
    0.37
     Neub
    0.37
    POSITIVE LOGITS
     ſ
    0.58
    achtige
    0.49
     ў
    0.47
     të
    0.45
     وَ
    0.44
    ɖ
    0.43
     være
    0.43
    proses
    0.42
    akkan
    0.42
    ak
    0.42
    Activations Density 1.342%

    No Known Activations