© 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. 51162
    Prev
    Next
    INDEX
    Explanations

    AI training data and biases

    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
    1
    0.53
    4
    0.50
    ∙
    0.49
    Khi
    0.48
    Vì
    0.48
    8
    0.48
    League
    0.47
    6
    0.47
    Ü
    0.47
    pués
    0.47
    POSITIVE LOGITS
     topologies
    0.46
    ার্থী
    0.45
    प्पू
    0.44
     tackling
    0.44
     Proposals
    0.43
    듄
    0.43
     previews
    0.43
     उठाए
    0.43
     outlining
    0.42
    ソニック
    0.42
    Activations Density 0.007%

    No Known Activations