© 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. 233625
    Prev
    Next
    INDEX
    Explanations

    understand aspartame

    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
     ն
    0.55
     մ
    0.54
     セ
    0.52
     กม
    0.50
     հ
    0.50
     δημο
    0.50
     اﻻ
    0.50
     სა
    0.49
     மேலும்
    0.49
     завдання
    0.47
    POSITIVE LOGITS
    stack
    0.48
    rover
    0.48
    طاء
    0.48
    Hi
    0.47
    ij
    0.47
    iet
    0.47
    sides
    0.46
    r
    0.46
    run
    0.46
    ir
    0.45
    Activations Density 0.001%

    No Known Activations