© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 52811
    Prev
    Next
    INDEX
    Explanations

    programming code constructs

    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
    Negative Logits
     enjoyed
    0.42
    ARIA
    0.42
     తన
    0.40
    Comma
    0.40
    May
    0.40
    IAT
    0.39
     noss
    0.39
    Ậ
    0.39
    Getter
    0.39
    Explain
    0.39
    POSITIVE LOGITS
    if
    0.47
    先把
    0.41
     if
    0.41
    नामेंट
    0.39
    SplashScreen
    0.39
    ii
    0.39
    ini
    0.39
    iii
    0.38
    昷
    0.38
    ersch
    0.38
    Activations Density 0.018%

    No Known Activations