© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 212258
    Prev
    Next
    INDEX
    Explanations

    technical or specific domain terms

    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_40_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
     soluzione
    0.43
    Okno
    0.41
    假設
    0.41
    놉
    0.40
    CNS
    0.39
    ಲೇ
    0.38
     উপভোগ
    0.38
     geom
    0.37
     namanya
    0.37
     зага
    0.37
    POSITIVE LOGITS
    ô
    0.37
    orong
    0.36
    ienes
    0.36
     electoral
    0.36
     Counting
    0.36
    adult
    0.36
    ารย์
    0.36
    ach
    0.35
    からない
    0.35
     ಅಂ
    0.35
    Activations Density 0.000%

    No Known Activations