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

    Neuronpedia

    Jacobian LensNEW
    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. 62971
    Prev
    Next
    INDEX
    Explanations

    `function` or `intersection`

    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
    𒅴
    0.54
     svaki
    0.49
    𝕒
    0.48
    testAvg
    0.47
     составля
    0.47
    𝗰
    0.47
    등급
    0.46
    ྗ
    0.46
     اجيب
    0.46
    goài
    0.45
    POSITIVE LOGITS
     is
    0.47
     intersecting
    0.47
    刚
    0.44
    MORE
    0.43
     failures
    0.43
     final
    0.42
     intersection
    0.41
    Diamonds
    0.41
     sessions
    0.41
    I
    0.40
    Activations Density 0.002%

    No Known Activations