© 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. 126104
    Prev
    Next
    INDEX
    Explanations

    direct comparisons

    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
    utiérrez
    0.52
    茭
    0.52
    ное
    0.50
    წიფ
    0.49
    ática
    0.47
    ционный
    0.47
    стый
    0.47
    ágico
    0.46
    魄
    0.46
    阊
    0.46
    POSITIVE LOGITS
     lim
    0.49
     q
    0.48
     iff
    0.46
     WARRANTIES
    0.44
     n
    0.43
     එව
    0.42
     margins
    0.41
     тоді
    0.41
     voire
    0.41
    調べ
    0.40
    Activations Density 0.002%

    No Known Activations