© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43087
    Prev
    Next
    INDEX
    Explanations

    defending champions

    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
    Not in Any Lists

    No Comments

    Negative Logits
     its
    -1.84
     has
    -1.80
     itself
    -1.72
     always
    -1.71
     or
    -1.62
     is
    -1.34
    ["_
    -1.31
     this
    -1.30
     already
    -1.29
     was
    -1.27
    POSITIVE LOGITS
     themselves
    3.03
    themselves
    2.06
     nhau
    2.05
     Their
    1.90
     leurs
    1.89
    Their
    1.88
    各自
    1.88
     their
    1.85
    respectively
    1.84
    their
    1.83
    Activations Density 0.615%

    No Known Activations