© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 204362
    Prev
    Next
    INDEX
    Explanations

    evaluation and description

    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
    ᓛ
    0.40
    ellen
    0.40
     lunch
    0.39
    allenges
    0.39
     í
    0.39
    iyu
    0.38
     mid
    0.38
    rangle
    0.38
    science
    0.38
    ichter
    0.38
    POSITIVE LOGITS
     Smooth
    0.38
    روش
    0.38
    Smooth
    0.37
     administração
    0.37
    کور
    0.37
    ็น
    0.35
    ประเทศ
    0.35
    弼
    0.35
    著名的
    0.34
    Isolated
    0.34
    Activations Density 0.000%

    No Known Activations