© 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. 90655
    Prev
    Next
    INDEX
    Explanations

    data than, full disc, candidate can

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

    language translation and understanding

    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
    a
    0.46
     voisines
    0.45
     maddenin
    0.45
    os
    0.45
    la
    0.44
     voisin
    0.43
     hona
    0.43
     offences
    0.43
    your
    0.42
     pondering
    0.42
    POSITIVE LOGITS
     Ві
    0.48
    屉
    0.46
    曲線
    0.46
    价比
    0.46
    นิ
    0.45
    ⌀
    0.44
     curve
    0.43
    ícios
    0.43
    transmitted
    0.43
     丶
    0.43
    Activations Density 0.001%

    No Known Activations