© 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. 9-GEMMASCOPE-2-RES-16K
    7. 80
    Prev
    Next
    INDEX
    Explanations

    delete key, forget all

    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_9_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
    ر
    1.83
    र
    1.80
    मा
    1.79
     iar
    1.69
    ка
    1.62
    なります
    1.55
     upd
    1.53
    an
    1.51
    态
    1.50
     fright
    1.49
    POSITIVE LOGITS
     khỏi
    1.70
    ⓷
    1.50
     therefrom
    1.46
    掉
    1.46
     connotations
    1.45
    нные
    1.45
    此之外
    1.44
     annihil
    1.44
    పో
    1.41
    zás
    1.41
    Activations Density 5.342%

    No Known Activations