© 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. 170559
    Prev
    Next
    INDEX
    Explanations

    or rejected, was driving, prospective users

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

    tone and feelings

    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
    Negative Logits
    izing
    0.50
    izable
    0.48
    ogo
    0.47
     reclam
    0.47
     스트
    0.47
    ij
    0.47
    場所
    0.46
    𝑖
    0.46
    á
    0.45
    âu
    0.45
    POSITIVE LOGITS
     IW
    0.54
     Replication
    0.45
     UK
    0.44
    θεί
    0.44
     arz
    0.44
    сть
    0.43
     препаратов
    0.43
     ilgili
    0.43
     SCGS
    0.42
    涪
    0.42
    Activations Density 0.001%

    No Known Activations