© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 105966
    Prev
    Next
    INDEX
    Explanations

    Law and covenant

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    s
    0.60
     jud
    0.59
     surprise
    0.50
     diminu
    0.48
    ﻖ
    0.48
     pronounced
    0.48
     descripción
    0.48
     dificult
    0.48
    та
    0.47
     calma
    0.47
    POSITIVE LOGITS
    蝟
    0.54
     노트
    0.53
     Eating
    0.53
     Oil
    0.51
    venty
    0.51
     Relationships
    0.51
     Vorteile
    0.50
    boek
    0.50
     ilişk
    0.50
     olefins
    0.50
    Activations Density 0.000%

    No Known Activations