© 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. 168525
    Prev
    Next
    INDEX
    Explanations

    specific components or attributes

    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
    会員
    0.49
     portefeuille
    0.46
     जिम्मेदारी
    0.44
    鏉
    0.43
    ]</
    0.43
    龧
    0.43
     చా
    0.43
    會員
    0.42
    जानिए
    0.42
    ശന
    0.41
    POSITIVE LOGITS
     veins
    0.57
     arterial
    0.54
     artery
    0.52
     vein
    0.51
     oxidative
    0.47
     rosin
    0.46
     bushings
    0.45
     angled
    0.44
     sarcom
    0.44
     e
    0.44
    Activations Density 0.007%

    No Known Activations