© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 62735
    Prev
    Next
    INDEX
    Explanations

    places in Connecticut

    np_acts-logits-general · gemini-2.5-flash-lite

    reasons signal up to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Aline
    0.49
     Cedric
    0.48
     limitations
    0.46
    ーン
    0.45
     Irish
    0.45
     inclusivity
    0.45
    架
    0.45
     dealers
    0.44
     Congratulations
    0.44
     Coulter
    0.44
    POSITIVE LOGITS
     وهو
    0.64
     הוא
    0.56
     เขา
    0.52
     comprado
    0.52
     uređ
    0.50
     เข
    0.49
     المر
    0.49
     ນ
    0.49
     العص
    0.49
     ඔහු
    0.47
    Activations Density 0.000%

    No Known Activations