© 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. 12765
    Prev
    Next
    INDEX
    Explanations

    literacy and reading skills for children

    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
    Not in Any Lists

    No Comments

    Negative Logits
    엣
    0.42
    রস
    0.42
     философ
    0.40
    PayPal
    0.39
     (++
    0.38
    隈
    0.38
     pelanggan
    0.38
     skór
    0.38
    ション
    0.37
    ϑ
    0.37
    POSITIVE LOGITS
     literacy
    1.68
     Literacy
    1.55
     reading
    1.52
     Reading
    1.34
    Reading
    1.27
     literate
    1.26
     READING
    1.24
    reading
    1.23
     읽
    1.19
     lettura
    1.19
    Activations Density 0.020%

    No Known Activations