© 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. 205777
    Prev
    Next
    INDEX
    Explanations

    Immediate actions, concepts, identifying

    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
     interpreting
    0.44
     Interpretation
    0.44
     Técnica
    0.43
    物
    0.43
     Default
    0.43
     Issued
    0.42
     出
    0.40
     Currency
    0.40
     imping
    0.40
     Tween
    0.40
    POSITIVE LOGITS
     hostages
    0.57
    Ꮥ
    0.53
    ಯೇ
    0.51
     anecdotes
    0.49
     tellus
    0.49
     poets
    0.49
     barns
    0.48
    旣
    0.48
     devastated
    0.48
     entertainers
    0.48
    Activations Density 0.000%

    No Known Activations