© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 92505
    Prev
    Next
    INDEX
    Explanations

    scientific and factual statements

    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
    靣
    0.45
     或
    0.45
    prite
    0.44
     lattice
    0.44
     또는
    0.44
    ivariate
    0.44
     توسط
    0.44
     見
    0.43
    _
    0.43
    ่า
    0.43
    POSITIVE LOGITS
     créditos
    0.45
     clinics
    0.44
     Policía
    0.42
     constitución
    0.42
     constituencies
    0.40
     observación
    0.40
     independencia
    0.40
     specialise
    0.40
     attractions
    0.40
     Chambers
    0.39
    Activations Density 0.006%

    No Known Activations