© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31596
    Prev
    Next
    INDEX
    Explanations

    relations between existent

    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
    -1.37
     as
    -1.16
     c
    -1.13
     not
    -1.05
     nonché
    -1.01
    them
    -0.98
     what
    -0.94
     always
    -0.93
     easy
    -0.90
     to
    -0.89
    POSITIVE LOGITS
     they
    1.56
     we
    1.24
     verla
    1.05
    sistente
    0.98
     brille
    0.98
    ONAUT
    0.95
    ojo
    0.94
     pály
    0.94
     duiz
    0.94
     it
    0.92
    Activations Density 0.001%

    No Known Activations