© 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. 3108
    Prev
    Next
    INDEX
    Explanations

    html structure

    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
     suka
    1.35
     roused
    1.27
     berada
    1.26
     relat
    1.26
    த
    1.24
     هو
    1.24
     ascends
    1.24
     meninas
    1.23
    Ϊ
    1.22
     pissed
    1.22
    POSITIVE LOGITS
    ください
    1.33
    kannya
    1.26
    िया
    1.24
    se
    1.23
    dung
    1.20
    slack
    1.20
    lumat
    1.17
    作用
    1.17
    ia
    1.15
    platz
    1.15
    Activations Density 0.156%

    No Known Activations