© 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-65K
    7. 64156
    Prev
    Next
    INDEX
    Explanations

    concepts or actions

    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_65k_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
    escol
    0.52
    sser
    0.50
    vania
    0.49
    ו
    0.49
     राउ
    0.47
     आपकी
    0.46
     قائ
    0.46
    o
    0.45
    ed
    0.45
    volent
    0.44
    POSITIVE LOGITS
    otá
    0.46
     November
    0.46
    ítható
    0.43
    坐标
    0.43
     দারি
    0.42
     Dieser
    0.42
    뺄
    0.42
    妸
    0.41
    November
    0.41
    酈
    0.41
    Activations Density 0.002%

    No Known Activations