© 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. 30072
    Prev
    Next
    INDEX
    Explanations

    Michigan or other addresses

    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
     would
    -1.42
     what
    -1.39
     Perhaps
    -1.35
     such
    -1.34
     so
    -1.33
     perhaps
    -1.30
     might
    -1.28
     could
    -1.27
     makes
    -1.24
     made
    -1.23
    POSITIVE LOGITS
    などが
    1.21
    0
    1.16
    などを
    1.16
    <bos>
    1.13
    個人的には
    1.12
    oluble
    1.11
     deliciously
    1.11
     relentless
    1.08
     masterful
    1.06
     Parlement
    1.05
    Activations Density 0.145%

    No Known Activations