© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 62870
    Prev
    Next
    INDEX
    Explanations

    speed or distance

    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
    b
    0.55
    anime
    0.52
    parcel
    0.49
    in
    0.47
    component
    0.47
    ality
    0.47
    fer
    0.47
    alir
    0.46
    ins
    0.46
     സോ
    0.46
    POSITIVE LOGITS
     eines
    0.46
     pleinement
    0.44
    鿉
    0.43
     fully
    0.42
    一场
    0.42
     unequivocally
    0.42
     följande
    0.41
     photonic
    0.41
     erhe
    0.41
     approxim
    0.40
    Activations Density 0.023%

    No Known Activations