© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 220752
    Prev
    Next
    INDEX
    Explanations

    hand-over period

    np_acts-logits-general · gemini-2.5-flash-lite

    Since transformers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     深
    0.58
     kapital
    0.55
     関
    0.51
    اني
    0.50
    時代
    0.50
     充電
    0.49
    рун
    0.48
     historischen
    0.48
    資本
    0.48
    تي
    0.47
    POSITIVE LOGITS
     }}^{
    0.43
    eyse
    0.43
    Enders
    0.42
    igay
    0.41
     evacuate
    0.40
    en
    0.40
    iculas
    0.40
    ing
    0.39
     چاہیے
    0.39
    emm
    0.39
    Activations Density 0.002%

    No Known Activations