© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 51893
    Prev
    Next
    INDEX
    Explanations

    machines perform automatic

    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_31_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
    ↵↵
    0.49
    ↵
    0.45
     .
    0.43
    iences
    0.41
    iques
    0.40
    তী
    0.39
     ans
    0.39
    shad
    0.39
    cutaneous
    0.39
    yan
    0.38
    POSITIVE LOGITS
    紂
    0.46
     escritório
    0.46
    忔
    0.45
     ஊழிய
    0.45
     ciek
    0.44
     подачи
    0.43
     mlijeka
    0.43
     целях
    0.43
     родствен
    0.42
    注意事项
    0.42
    Activations Density 0.000%

    No Known Activations