© 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. 220050
    Prev
    Next
    INDEX
    Explanations

    abstract concepts and actions

    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
     Games
    0.44
     Six
    0.39
     SIX
    0.39
    search
    0.38
    ni
    0.37
     GAMES
    0.37
    pi
    0.36
     six
    0.36
     Rating
    0.36
    魔
    0.36
    POSITIVE LOGITS
    হতের
    0.46
    𝕣
    0.40
     ­
    0.40
     cinereo
    0.40
     dentro
    0.40
     น่ะ
    0.40
     rằng
    0.39
     внутри
    0.39
    нутри
    0.39
    sparsebundle
    0.39
    Activations Density 0.005%

    No Known Activations