© 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. 144506
    Prev
    Next
    INDEX
    Explanations

    already undergone

    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
    र
    0.49
    阶
    0.49
    Nunca
    0.48
    ਕ
    0.47
    노
    0.47
    പോലെ
    0.47
    alista
    0.47
    여
    0.47
    修行
    0.46
    ك
    0.46
    POSITIVE LOGITS
     improvised
    0.52
     using
    0.46
     random
    0.46
     method
    0.45
     bevorzug
    0.44
     init
    0.44
     ex
    0.44
     among
    0.44
     donned
    0.43
     values
    0.43
    Activations Density 0.007%

    No Known Activations