© 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. 170405
    Prev
    Next
    INDEX
    Explanations

    common phrases after common words

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

    building an

    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
     DET
    0.48
    Are
    0.48
    رحله
    0.46
    ുകൊണ്ട
    0.46
     gb
    0.46
    ォ
    0.45
     BEN
    0.44
    ت
    0.44
     sempre
    0.44
     go
    0.43
    POSITIVE LOGITS
    striatis
    0.51
    akas
    0.48
    kovskij
    0.46
     affine
    0.46
    quets
    0.45
    TreeWidgetItem
    0.45
    hyp
    0.45
    covite
    0.45
    u
    0.44
    cx
    0.44
    Activations Density 0.000%

    No Known Activations