© 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. 210308
    Prev
    Next
    INDEX
    Explanations

    emails and tickets

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

    traditional programming

    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
     unclear
    0.49
    蚓
    0.49
     blinded
    0.48
     trained
    0.47
     meninggal
    0.47
    '),
    0.46
     salvaged
    0.46
     velcro
    0.45
     dosen
    0.44
     finisher
    0.44
    POSITIVE LOGITS
     كلمات
    0.57
     არს
    0.53
    ުގައި
    0.49
     পুন
    0.48
     गिरफ्तारी
    0.47
     Worte
    0.47
    詞
    0.47
    懲
    0.46
    大道
    0.46
    ය
    0.45
    Activations Density 0.000%

    No Known Activations