© 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. 38
    Prev
    Next
    INDEX
    Explanations

    place names

    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
     r
    0.32
     neutral
    0.32
     single
    0.28
    เหล
    0.27
    ound
    0.27
     inflex
    0.27
     C
    0.27
     dog
    0.26
     form
    0.26
     resp
    0.26
    POSITIVE LOGITS
     Balliye
    0.47
    ták
    0.45
     vijf
    0.44
    ścic
    0.44
    ၡ
    0.43
    ávání
    0.42
    uhi
    0.42
    海南
    0.42
    ólogos
    0.41
    apuris
    0.41
    Activations Density 0.324%

    No Known Activations