© 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. 6593
    Prev
    Next
    INDEX
    Explanations

    numerical settings and probabilities

    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
    re
    0.51
    ੁ
    0.49
    ur
    0.49
    手
    0.48
    综合
    0.46
    im
    0.46
    首先
    0.45
    ]["
    0.44
    jskich
    0.44
    operatorname
    0.43
    POSITIVE LOGITS
     conspicuously
    0.48
    စျေး
    0.47
     ஒற்று
    0.47
     botched
    0.46
     உப்பு
    0.46
     <=
    0.46
     Massacre
    0.44
     ترکیه
    0.44
     windfall
    0.44
    त्कार
    0.43
    Activations Density 0.001%

    No Known Activations