© 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. 22-GEMMASCOPE-2-RES-16K
    7. 10269
    Prev
    Next
    INDEX
    Explanations

    python -m venv

    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_22_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
     exchange
    0.97
    igata
    0.91
    saw
    0.90
    ために
    0.89
     গাড়ী
    0.89
    finders
    0.89
    $>$
    0.88
     derm
    0.87
     نحاول
    0.86
     autore
    0.86
    POSITIVE LOGITS
    D
    0.98
     comentado
    0.89
    ˏ
    0.88
    Marriage
    0.88
     silvest
    0.87
    Complaint
    0.87
    L
    0.86
    P
    0.86
    S
    0.86
     понима
    0.85
    Activations Density 0.034%

    No Known Activations