© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 79459
    Prev
    Next
    INDEX
    Explanations

    acronyms followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ſe
    -1.00
    imize
    -0.97
    SOME
    -0.96
    хо
    -0.95
     geene
    -0.93
    Bangladesh
    -0.91
    衄
    -0.91
    remaining
    -0.90
     gyere
    -0.90
     kuah
    -0.90
    POSITIVE LOGITS
     very
    0.93
     even
    0.87
     delve
    0.86
    荩
    0.85
     there
    0.85
     measure
    0.84
    せば
    0.82
     venturing
    0.81
     as
    0.81
     Settle
    0.81
    Activations Density 0.110%

    No Known Activations