© 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. 10-GEMMASCOPE-RES-131K
    7. 15661
    Prev
    Next
    INDEX
    Explanations

    sharing links to patents

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    }$.
    -1.80
     and
    -1.37
    \}$.
    -1.26
    😤
    -1.23
    🫶
    -1.21
     mision
    -1.20
     itali
    -1.20
    นี้
    -1.20
     until
    -1.20
    CTION
    -1.19
    POSITIVE LOGITS
    _
    2.20
    :
    1.84
    those
    1.54
    -
    1.50
     those
    1.50
    だいたい
    1.41
     sostuvo
    1.39
    they
    1.38
     eradic
    1.35
     cualidades
    1.35
    Activations Density 0.135%

    No Known Activations