© 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. 246733
    Prev
    Next
    INDEX
    Explanations

    will be, is an, see things

    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
     idolat
    0.54
    ल
    0.49
    scr
    0.48
    <start_of_image>
    0.48
     ing
    0.47
     eros
    0.46
     sulph
    0.46
     istri
    0.46
     adolescents
    0.45
     abys
    0.45
    POSITIVE LOGITS
    িলিয়া
    0.57
    浱
    0.57
     Connector
    0.56
    কলাপ
    0.54
    ارين
    0.53
    เชสเตอร์
    0.52
    碚
    0.52
    মিটার
    0.51
    ременно
    0.51
    在于
    0.51
    Activations Density 0.000%

    No Known Activations