© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 137781
    Prev
    Next
    INDEX
    Explanations

    space and geography descriptions

    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_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     upon
    0.44
    жный
    0.40
    事务
    0.37
    ալ
    0.37
     violations
    0.37
     哈
    0.36
    摆
    0.36
     ...,
    0.36
     উভয়
    0.35
     thicken
    0.35
    POSITIVE LOGITS
    ؟!
    0.46
    サイズの
    0.43
    ᅲ
    0.42
    ucky
    0.41
     আপাত
    0.41
    teaser
    0.41
    shoz
    0.40
    herme
    0.39
     Sinne
    0.39
    invite
    0.38
    Activations Density 0.001%

    No Known Activations