© 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-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 13411
    Prev
    Next
    INDEX
    Explanations

    code and data structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_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
     signIn
    0.52
    ляма
    0.50
    氀
    0.50
    લ
    0.49
    ̀
    0.48
     обновления
    0.47
     wade
    0.47
     activités
    0.47
    手間
    0.47
    ロ
    0.46
    POSITIVE LOGITS
    sty
    0.50
    maks
    0.49
    ()=>{
    0.45
    ks
    0.44
    maximal
    0.44
    sinx
    0.43
    can
    0.43
    maximum
    0.42
    ltk
    0.42
    npcs
    0.42
    Activations Density 0.000%

    No Known Activations