© 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. 7904
    Prev
    Next
    INDEX
    Explanations

    change, address, scan, dish

    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
    6
    0.47
    4
    0.47
    3
    0.46
    7
    0.46
    hishek
    0.44
    8
    0.43
    ducers
    0.43
    .
    0.42
    นี้
    0.40
    iteracy
    0.39
    POSITIVE LOGITS
     penchant
    0.42
     snd
    0.40
     clenched
    0.39
     playmaker
    0.39
     et
    0.38
     orthonormal
    0.38
    和田
    0.38
     principalement
    0.38
     başta
    0.37
    𓃵
    0.37
    Activations Density 0.112%

    No Known Activations