© 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. 31-GEMMASCOPE-2-RES-262K
    7. 55884
    Prev
    Next
    INDEX
    Explanations

    status about viscosity

    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_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     secara
    0.47
     inden
    0.47
     el
    0.45
     dalam
    0.45
    tronic
    0.45
    ized
    0.44
     von
    0.44
    imi
    0.43
    ixas
    0.43
    Ö
    0.43
    POSITIVE LOGITS
     BBB
    0.55
    𝔂
    0.55
     проверка
    0.53
     ніж
    0.52
    ㄼ
    0.52
    ৪
    0.52
    ㄺ
    0.51
    ᱘
    0.50
    𝓹
    0.49
     اہ
    0.49
    Activations Density 0.005%

    No Known Activations