© 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. 114200
    Prev
    Next
    INDEX
    Explanations

    us or them

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

    frequently, urgent, metric, means

    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
    oczy
    0.49
     Hackney
    0.48
    받
    0.48
    ἦ
    0.47
    극한
    0.47
     accurate
    0.45
     Alessandra
    0.43
     Fewer
    0.43
    ರಳ
    0.43
    땡
    0.43
    POSITIVE LOGITS
     периоди
    0.47
     בני
    0.46
    j
    0.46
    alted
    0.45
    ➖
    0.45
    ធាតុ
    0.44
     syndromes
    0.44
    vital
    0.43
    actionBar
    0.43
    alt
    0.43
    Activations Density 0.000%

    No Known Activations