© 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. 31240
    Prev
    Next
    INDEX
    Explanations

    searching the

    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
     a
    -1.45
     its
    -1.40
     it
    -1.40
     this
    -1.34
     that
    -1.33
     everything
    -1.20
     utaf
    -1.18
     such
    -1.17
     what
    -1.16
     those
    -1.15
    POSITIVE LOGITS
     the
    3.97
    ˃
    1.19
     The
    1.16
    InThe
    1.16
     cherchés
    1.16
    inthe
    1.11
    sona
    1.09
    lblNewLabel
    1.09
     [];
    1.07
     peruan
    1.06
    Activations Density 0.132%

    No Known Activations