© 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. 107221
    Prev
    Next
    INDEX
    Explanations

    tech/software/research terms

    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
     CANCEL
    -0.76
    Meli
    -0.76
    nehå
    -0.76
     Azo
    -0.75
     nemesis
    -0.73
    વા
    -0.73
    ypso
    -0.73
     ose
    -0.72
     cáncer
    -0.72
    LNG
    -0.72
    POSITIVE LOGITS
    Interview
    1.04
     Interview
    0.98
     interview
    0.94
    Minute
    0.79
     complexes
    0.70
     Louisiana
    0.70
     минуту
    0.70
     listens
    0.69
    interview
    0.69
     Las
    0.69
    Activations Density 0.034%

    No Known Activations