© 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. 47265
    Prev
    Next
    INDEX
    Explanations

    you may

    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
    prender
    -1.19
    seemed
    -1.15
     WOULD
    -1.03
     RECOMMEND
    -1.03
    odine
    -1.03
    oved
    -1.02
    migrationBuilder
    -1.02
     można
    -1.01
    TTTT
    -1.01
     ofrece
    -1.00
    POSITIVE LOGITS
     find
    2.27
     think
    1.99
     have
    1.97
     want
    1.87
     not
    1.60
     like
    1.59
     already
    1.53
     yourself
    1.51
     finds
    1.48
     even
    1.38
    Activations Density 0.039%

    No Known Activations