© 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. 92327
    Prev
    Next
    INDEX
    Explanations

    company evaluation and rights

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

    application/file types

    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
     சிறந்த
    0.45
     когда
    0.44
     приго
    0.43
     чудо
    0.43
     када
    0.41
     проде
    0.41
    quando
    0.41
     ду
    0.41
     नांद
    0.41
    ☉
    0.40
    POSITIVE LOGITS
    js
    0.48
     isl
    0.46
     selaku
    0.45
     应用
    0.42
    leyin
    0.42
    acuation
    0.41
     করছিল
    0.41
     jako
    0.40
    是因為
    0.40
    bs
    0.40
    Activations Density 0.000%

    No Known Activations