© 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. 93996
    Prev
    Next
    INDEX
    Explanations

    Communication, work, and theory

    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
    ？）
    0.52
    Pseudo
    0.50
    })
    0.48
     ус
    0.47
    はない
    0.47
    ？”
    0.46
    ?");
    0.45
     आपत्ति
    0.44
    validate
    0.44
    delete
    0.43
    POSITIVE LOGITS
    ourses
    0.49
    味料
    0.49
    lerinin
    0.47
     labor
    0.46
    玑
    0.45
     διά
    0.45
    ాల్లో
    0.44
    UTHER
    0.44
     slope
    0.43
     slopes
    0.43
    Activations Density 0.005%

    No Known Activations