© 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. 31-GEMMASCOPE-2-RES-16K
    7. 104
    Prev
    Next
    INDEX
    Explanations

    numbers and code

    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_31_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
     ډول
    0.17
     एखाद्या
    0.17
     appease
    0.17
     هم
    0.17
    cription
    0.17
     ٻ
    0.16
     في
    0.16
     اه
    0.16
     StringSet
    0.16
     sabotage
    0.16
    POSITIVE LOGITS
    0
    0.30
    -
    0.27
    8
    0.25
    ０
    0.25
     दिवसीय
    0.25
    5
    0.25
    р
    0.24
    он
    0.24
    4
    0.24
    %-
    0.23
    Activations Density 0.717%

    No Known Activations