© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 137737
    Prev
    Next
    INDEX
    Explanations

    `compiler` `Include` `Ground` `**`

    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
    Not in Any Lists

    No Comments

    Negative Logits
     searched
    0.53
    ı
    0.50
    ravel
    0.47
    olding
    0.46
     grooms
    0.46
    OF
    0.45
     buscador
    0.44
    iling
    0.44
    ien
    0.44
    of
    0.43
    POSITIVE LOGITS
    ر
    0.52
     Nut
    0.51
     Leo
    0.50
     Namely
    0.47
     Privacidade
    0.46
     Foli
    0.46
     Vue
    0.45
     Cana
    0.45
     Haag
    0.45
     Zden
    0.45
    Activations Density 0.002%

    No Known Activations