© 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. 31646
    Prev
    Next
    INDEX
    Explanations

    filenames and code fragments

    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
     with
    -1.02
     as
    -0.98
     after
    -0.94
     from
    -0.94
     for
    -0.94
     Dostupné
    -0.93
     With
    -0.92
     despite
    -0.91
     through
    -0.91
     of
    -0.91
    POSITIVE LOGITS
     sirop
    1.09
     bisous
    1.07
    actually
    1.07
     casque
    1.06
     benevol
    1.00
    becomes
    0.98
     maillot
    0.98
     capot
    0.98
     Suara
    0.98
     muſt
    0.96
    Activations Density 0.001%

    No Known Activations