© 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. 41641
    Prev
    Next
    INDEX
    Explanations

    explaining phenomena or developments

    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
    encoded
    0.49
    angk
    0.48
    orchid
    0.46
    ल
    0.46
    ourced
    0.45
    processed
    0.45
    
    0.45
    strength
    0.44
    ਿਲ
    0.44
    ᕝ
    0.44
    POSITIVE LOGITS
    Disagree
    0.50
    0.42
    డు
    0.39
     environment
    0.38
     रहे
    0.37
    Contrary
    0.37
    Affected
    0.37
     rumen
    0.37
     disagreed
    0.37
    Primer
    0.37
    Activations Density 0.004%

    No Known Activations