© 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. 71364
    Prev
    Next
    INDEX
    Explanations

    Unusual products, stars, research, official

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

    however introducing contrasting clauses

    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
    Not in Any Lists

    No Comments

    Negative Logits
    engkap
    0.47
     animale
    0.46
    cmds
    0.46
     मधुमेह
    0.44
     comidas
    0.44
    ifestyle
    0.43
    ご紹介
    0.43
    ἂ
    0.43
    филлер
    0.43
    শেষ
    0.42
    POSITIVE LOGITS
    歪
    0.45
     cousin
    0.44
     输出
    0.42
     heg
    0.42
    गढ़
    0.41
     since
    0.41
     indiscriminate
    0.41
    poon
    0.40
     distorted
    0.40
     epicenter
    0.40
    Activations Density 0.000%

    No Known Activations