© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 103696
    Prev
    Next
    INDEX
    Explanations

    proud of it

    np_acts-logits-general · gemini-2.5-flash-lite

    week and weekend plans

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    }.$$
    0.49
     ଗ
    0.47
    🙃
    0.47
    nor
    0.46
    Glue
    0.46
    Sheets
    0.45
    rot
    0.45
    implies
    0.44
    balls
    0.44
    ।”
    0.43
    POSITIVE LOGITS
     dilapidated
    0.54
     witnessed
    0.50
     ì
    0.50
     licensed
    0.48
     documentary
    0.48
     conducting
    0.48
     witnessing
    0.47
    olutamente
    0.47
    その
    0.46
     payment
    0.46
    Activations Density 0.000%

    No Known Activations