© 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. 77653
    Prev
    Next
    INDEX
    Explanations

    difference in her health

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

    reversed text

    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
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.40
    ͋
    0.40
    CameraController
    0.38
    ttier
    0.38
    ɾ
    0.38
    vpc
    0.37
    ક્સ
    0.37
    testers
    0.36
    apie
    0.36
    vezet
    0.36
    POSITIVE LOGITS
    쌓
    0.38
    Valentine
    0.37
     분류
    0.36
     돌아
    0.35
     Hartman
    0.35
     Institutions
    0.35
     להת
    0.35
     불구하고
    0.35
    Short
    0.34
     фран
    0.34
    Activations Density 0.002%

    No Known Activations