© 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-65K
    7. 57248
    Prev
    Next
    INDEX
    Explanations

    conditional execution

    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_65k_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
    秸
    0.34
     बाइ
    0.32
     σημ
    0.32
     국가
    0.31
     බො
    0.31
     suede
    0.31
     HN
    0.31
     Schwerpunkt
    0.31
    WOOD
    0.30
    、
    0.30
    POSITIVE LOGITS
     দিত
    0.50
     wäre
    0.46
     skulle
    0.46
     Would
    0.45
     করতাম
    0.44
     haría
    0.44
     sarebbe
    0.43
     hätten
    0.43
     auraient
    0.43
     würden
    0.42
    Activations Density 0.053%

    No Known Activations