© 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. 22-GEMMASCOPE-RES-131K
    7. 73395
    Prev
    Next
    INDEX
    Explanations

    headers for notes or comments

    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_22/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
    怱
    -1.04
     aktuell
    -1.03
    ftar
    -1.03
    matthew
    -1.00
     outcast
    -0.99
    steven
    -0.98
     便利
    -0.96
    😊
    -0.94
    NOVA
    -0.93
    pochette
    -0.92
    POSITIVE LOGITS
     particularly
    1.25
     about
    1.23
     regarding
    1.17
     any
    1.15
     especially
    1.13
    opheles
    1.12
     despite
    1.08
     includes
    1.05
     could
    1.02
    ̿
    1.02
    Activations Density 0.020%

    No Known Activations