© 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. 32314
    Prev
    Next
    INDEX
    Explanations

    armed, maintain, networks, learn

    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
    精致
    0.47
     synov
    0.46
     gurus
    0.45
    𝐽
    0.44
     photosynthesis
    0.44
     okolo
    0.44
     antiseptic
    0.44
     solutes
    0.43
     guru
    0.43
    四季
    0.43
    POSITIVE LOGITS
    ერ
    0.52
    3
    0.47
    the
    0.44
    arsk
    0.43
    autom
    0.42
     präsent
    0.41
    тун
    0.41
    ሚ
    0.41
    arn
    0.41
     اعتق
    0.41
    Activations Density 0.002%

    No Known Activations