© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 153217
    Prev
    Next
    INDEX
    Explanations

    duration or sequence

    np_acts-logits-general · gemini-2.5-flash-lite

    gout, parcel, fluid, field

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     falam
    0.50
    airplane
    0.50
    сной
    0.48
    invalidate
    0.48
     balloon
    0.48
    ieten
    0.47
     )
    0.47
     vliegt
    0.46
    Idaho
    0.46
     أيضا
    0.46
    POSITIVE LOGITS
     Sessions
    0.48
    子女
    0.44
     Noting
    0.43
    提出的
    0.43
    ('.',
    0.43
     준비
    0.42
     प्राइम
    0.42
    ukas
    0.42
    当下
    0.42
    𒄩
    0.41
    Activations Density 0.000%

    No Known Activations