© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 49563
    Prev
    Next
    INDEX
    Explanations

    final or private declarations

    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
    Not in Any Lists

    No Comments

    Negative Logits
     that
    -1.78
     what
    -1.48
     there
    -1.38
     which
    -1.22
     one
    -1.17
     was
    -1.13
     it
    -1.11
     where
    -1.10
     not
    -1.09
     your
    -1.07
    POSITIVE LOGITS
    final
    4.88
     final
    4.81
     finally
    3.66
    最后
    3.22
    Finally
    3.19
     the
    2.97
     finalmente
    2.89
     Finally
    2.83
     FINAL
    2.81
    最後
    2.80
    Activations Density 0.009%

    No Known Activations