© 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. 40-GEMMASCOPE-2-RES-262K
    7. 164632
    Prev
    Next
    INDEX
    Explanations

    adopted

    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_40_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
     ajustar
    0.47
     mated
    0.45
     vortices
    0.42
    ′,
    0.42
    ͤ
    0.41
     nucleons
    0.40
     Ciò
    0.40
     hybridization
    0.40
     האט
    0.40
     readjust
    0.39
    POSITIVE LOGITS
     Kur
    0.40
    show
    0.39
     Litter
    0.38
    pel
    0.38
    hay
    0.37
    bru
    0.37
    لے
    0.37
     Pel
    0.36
    p
    0.36
    Deja
    0.35
    Activations Density 0.000%

    No Known Activations