© 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. 24739
    Prev
    Next
    INDEX
    Explanations

    local chat channel

    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
    iph
    0.49
    unters
    0.46
     強
    0.46
    強調
    0.46
     uitge
    0.43
    genres
    0.42
    諸
    0.42
    ై
    0.42
    賃
    0.42
     重
    0.41
    POSITIVE LOGITS
     coffee
    0.53
     beso
    0.52
     ono
    0.52
     local
    0.48
     palabra
    0.48
     paling
    0.47
     ammonia
    0.46
    జయ
    0.46
     area
    0.45
     poni
    0.45
    Activations Density 0.001%

    No Known Activations