© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 19074
    Prev
    Next
    INDEX
    Explanations

    analog circuits

    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
     etik
    0.46
     FIELDS
    0.46
     nebude
    0.44
     priorit
    0.42
     Relationships
    0.41
     முதல்வர்
    0.41
    హా
    0.41
    ন
    0.41
    াসা
    0.40
     sympathies
    0.40
    POSITIVE LOGITS
     дет
    0.55
     нео
    0.47
    
    0.46
     зна
    0.46
    )});
    0.45
     защи
    0.45
     сле
    0.44
     тро
    0.44
    
    0.44
     Дет
    0.44
    Activations Density 0.002%

    No Known Activations