© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 57618
    Prev
    Next
    INDEX
    Explanations

    YEARS AND ABOVE

    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
     and
    -1.32
     in
    -1.02
     on
    -0.91
     млрд
    -0.89
     to
    -0.87
     млн
    -0.86
     with
    -0.86
    న
    -0.81
    要点
    -0.81
     of
    -0.81
    POSITIVE LOGITS
    above
    1.37
     above
    1.29
    Above
    1.16
     hereinafter
    1.14
     Poni
    1.12
    below
    1.11
     acima
    1.11
    左右
    1.06
     ABOVE
    1.05
    hereinafter
    1.05
    Activations Density 0.016%

    No Known Activations