© 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. 117258
    Prev
    Next
    INDEX
    Explanations

    block in

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

    poetic / archy / arc / building

    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
    ሎ
    0.56
    र्द
    0.53
    at
    0.52
    ла
    0.52
    르
    0.52
    пор
    0.51
    ા
    0.50
    މ
    0.50
    ری
    0.50
    ला
    0.48
    POSITIVE LOGITS
     dusk
    0.50
     deterrence
    0.50
     perturbation
    0.49
     liberalization
    0.48
     reconciliation
    0.47
     Peru
    0.46
     disruption
    0.46
     displaced
    0.46
     proton
    0.45
     transmutation
    0.45
    Activations Density 0.000%

    No Known Activations