© 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. 23602
    Prev
    Next
    INDEX
    Explanations

    delegitimize

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

    discovering specific entities

    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
    ن
    0.54
     officer
    0.48
    ني
    0.48
    conse
    0.47
    να
    0.46
     skills
    0.45
    生
    0.45
    teren
    0.44
    ન
    0.44
     leverage
    0.44
    POSITIVE LOGITS
     Nahi
    0.54
     Acá
    0.52
     Perkenalkan
    0.50
     Python
    0.50
     Burma
    0.49
     Rajasthan
    0.49
     Paise
    0.49
     Untuk
    0.48
     うる
    0.47
     Sudah
    0.47
    Activations Density 0.000%

    No Known Activations