© 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. 38698
    Prev
    Next
    INDEX
    Explanations

    motivates

    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
     cufflinks
    0.46
    eenth
    0.46
     magnitudes
    0.40
    vertex
    0.40
    theoretical
    0.40
    helix
    0.39
    as
    0.39
    i
    0.39
     symbolic
    0.39
     ۱
    0.38
    POSITIVE LOGITS
    废水
    0.54
     మాత్రమే
    0.51
    Resposta
    0.50
     पाणी
    0.49
    ଘ
    0.48
     પાણી
    0.48
    మ్
    0.47
    污水
    0.46
     безопасности
    0.46
     отве
    0.45
    Activations Density 0.007%

    No Known Activations