© 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. 1189
    Prev
    Next
    INDEX
    Explanations

    learning how to

    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
    such
    0.48
    Activated
    0.47
    Méd
    0.46
    цен
    0.45
    URANCE
    0.45
    KNOWN
    0.45
    USED
    0.44
    Requested
    0.44
    Ｕ
    0.44
    Ep
    0.44
    POSITIVE LOGITS
     on
    0.49
    ank
    0.48
    idae
    0.48
     intangible
    0.48
     to
    0.47
    ists
    0.47
     habit
    0.46
    ilst
    0.45
     habits
    0.45
     instincts
    0.45
    Activations Density 0.001%

    No Known Activations