© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 36695
    Prev
    Next
    INDEX
    Explanations

    blockchain, incorporated, modern devices

    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
     décide
    0.45
     décider
    0.43
    úl
    0.41
     其实
    0.40
    ⱨ
    0.40
     মূলত
    0.40
     пыта
    0.39
    旖
    0.39
     নির্ধারণ
    0.39
     Kenyan
    0.38
    POSITIVE LOGITS
    d
    0.51
     formulations
    0.45
    dif
    0.44
     seamless
    0.44
     Doremi
    0.42
     Stateful
    0.42
     differences
    0.41
     recognition
    0.41
     election
    0.41
    dependencies
    0.41
    Activations Density 0.002%

    No Known Activations