© 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. 141251
    Prev
    Next
    INDEX
    Explanations

    linking preceding and succeeding words

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

    data collection and source

    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
    讷
    0.50
    栝
    0.50
    كم
    0.48
    数字
    0.47
    ذور
    0.47
    德
    0.46
     UIText
    0.46
    ب
    0.46
    ׳
    0.45
     циф
    0.45
    POSITIVE LOGITS
    are
    0.58
    ai
    0.52
     Vestone
    0.50
    oy
    0.49
    opinion
    0.49
    ur
    0.46
     posicao
    0.45
    ｙ
    0.45
    arning
    0.44
     करीब
    0.44
    Activations Density 0.000%

    No Known Activations