© 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. 19806
    Prev
    Next
    INDEX
    Explanations

    relationship-based access

    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
    cute
    0.49
    ccbp
    0.49
    本当に
    0.48
    ta
    0.47
    transition
    0.47
    justice
    0.47
    t
    0.47
     मजाक
    0.47
    total
    0.46
    really
    0.46
    POSITIVE LOGITS
     เพราะ
    0.49
     передба
    0.46
     включа
    0.45
     ควร
    0.45
     diverses
    0.44
     inodes
    0.43
     plaat
    0.43
    牒
    0.43
     çeşitli
    0.43
     Sometimes
    0.43
    Activations Density 0.006%

    No Known Activations