© 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. 53-GEMMASCOPE-2-RES-262K
    7. 40996
    Prev
    Next
    INDEX
    Explanations

    PS questionauth claims

    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_53_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     लघु
    0.45
     disbursed
    0.37
     reprints
    0.37
    தான்
    0.37
     Rep
    0.36
     pronouncing
    0.36
    +}$,
    0.36
    冎
    0.36
    綗
    0.35
    tvrt
    0.35
    POSITIVE LOGITS
     auth
    0.47
    auth
    0.44
    DQ
    0.42
     relations
    0.41
     ends
    0.40
     admire
    0.38
     Ends
    0.38
     SHOW
    0.38
    Auth
    0.37
     admirers
    0.37
    Activations Density 0.000%

    No Known Activations