© 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. 16-GEMMASCOPE-2-RES-262K
    7. 4629
    Prev
    Next
    INDEX
    Explanations

    the start of a sentence

    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_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    _
    0.32
    and
    0.32
    un
    0.31
    ob
    0.30
    ar
    0.30
    ang
    0.30
    al
    0.29
    it
    0.29
    rän
    0.29
    ab
    0.28
    POSITIVE LOGITS
    .
    0.30
    ®.
    0.28
     unsuccessfully
    0.28
    ﻚ
    0.28
     моём
    0.25
    ۔
    0.25
     ผม
    0.25
     abruptly
    0.25
    मैंने
    0.25
    ཨ
    0.24
    Activations Density 0.000%

    No Known Activations