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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 249818
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     светло
    0.41
    𝐄
    0.40
    鹿
    0.40
     кри
    0.39
    ायल
    0.39
    è
    0.39
     reflective
    0.39
    镟
    0.38
     guidance
    0.38
     depressed
    0.37
    POSITIVE LOGITS
     intestines
    0.40
     evap
    0.40
     holog
    0.40
     intestino
    0.39
    opus
    0.38
     hikers
    0.38
     kites
    0.38
     intestin
    0.38
     Holog
    0.37
     surgeries
    0.37
    Activations Density 0.036%

    No Known Activations