© 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. 239770
    Prev
    Next
    INDEX
    Explanations

    video production team

    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
    version
    0.49
    ties
    0.44
     (
    0.42
    論
    0.42
     国
    0.41
     Additional
    0.41
    .”)
    0.40
    tained
    0.40
    Version
    0.40
    tion
    0.40
    POSITIVE LOGITS
     filmed
    0.48
     vídeos
    0.46
     videolar
    0.45
     slike
    0.45
    Ⲏ
    0.44
    员工
    0.44
     proizv
    0.44
    ẳng
    0.43
     eradicate
    0.43
     ovaj
    0.43
    Activations Density 0.010%

    No Known Activations