© 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. 40-GEMMASCOPE-2-RES-262K
    7. 193431
    Prev
    Next
    INDEX
    Explanations

    lists and code examples

    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_40_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
     coming
    0.40
    대학
    0.38
    呥
    0.38
     r
    0.37
     존재
    0.36
    흔
    0.35
     Cargill
    0.35
     POWER
    0.35
    ட்டிக்
    0.35
     udd
    0.35
    POSITIVE LOGITS
    тации
    0.42
     modernas
    0.41
    ]=='
    0.40
    حو
    0.40
    `],
    0.39
    žu
    0.38
    ✕
    0.37
    鹿
    0.37
    現代
    0.37
    Ẓ
    0.37
    Activations Density 0.000%

    No Known Activations