© 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. 205454
    Prev
    Next
    INDEX
    Explanations

    diverse topics and technical 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
    镂
    0.45
    qry
    0.40
     کمپیوٹر
    0.40
    အရေ
    0.40
    朗普
    0.39
     QUERY
    0.38
    齣
    0.38
    *\*
    0.38
    便宜
    0.38
    随意
    0.37
    POSITIVE LOGITS
     حكم
    0.38
    postos
    0.38
    cours
    0.38
    ")->
    0.37
    cont
    0.37
    갓
    0.37
     exalted
    0.36
     cam
    0.35
    ပေါ
    0.35
     implicit
    0.35
    Activations Density 0.000%

    No Known Activations