© 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. 6674
    Prev
    Next
    INDEX
    Explanations

    introduces a statement

    np_acts-logits-general · gemini-2.5-flash-lite

    phrases of metadiscourse and conversational asides that address the reader/listener, add emphasis or hedging, and frame or comment on the surrounding statement.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
    Анд
    0.41
     visant
    0.40
     illetve
    0.40
     destiné
    0.38
     તેમજ
    0.37
     जमकर
    0.37
     ensuring
    0.35
     പ്രവർത്തന
    0.35
     និង
    0.35
     क्रिप्ट
    0.34
    POSITIVE LOGITS
    ,
    0.59
     bahwa
    0.54
     rằng
    0.54
     أنه
    0.50
     there
    0.49
    ว่า
    0.45
     ότι
    0.45
     that
    0.44
     kwamba
    0.43
     bahawa
    0.43
    Activations Density 0.128%

    No Known Activations