© 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. 10686
    Prev
    Next
    INDEX
    Explanations

    non-English words

    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
    のは
    1.27
     pneumonia
    1.07
     trademark
    1.06
     magnification
    1.03
     natthi
    1.03
     catfish
    1.02
    ]*(
    1.02
     compressed
    1.00
     サ
    1.00
     deep
    1.00
    POSITIVE LOGITS
     üks
    1.20
     utilisateurs
    1.19
     propriétaires
    1.16
     ensayos
    1.15
    llä
    1.13
     katika
    1.13
    inizio
    1.12
     acredit
    1.12
     laboral
    1.10
    áticas
    1.10
    Activations Density 0.000%

    No Known Activations