© 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
    2. Gemma-3-4B-IT
    3. 17-GEMMASCOPE-2-RES-16K
    4. 10354
    Prev
    Next
    INDEX
    Explanations

    put on, put up, put yourself

    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
    부터
    2.24
    reveal
    2.23
    굶
    2.21
     partir
    2.14
    𝐠
    2.13
     immunoblot
    2.02
    ะไร
    2.01
    ޏ
    2.00
    ीडी
    1.98
    ان
    1.93
    POSITIVE LOGITS
     onus
    2.95
    ক
    2.71
     nervioso
    2.55
    monary
    2.51
     avanzada
    2.39
    ty
    2.36
     feas
    2.33
    ेंसिल
    2.30
     squarely
    2.30
    ו
    2.28
    Activations Density 0.181%

    No Known Activations