© 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. 173791
    Prev
    Next
    INDEX
    Explanations

    use to, responsible to, ability to

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

    assembly file, ASCII, clusters

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ل
    0.57
    લ
    0.50
    lasse
    0.48
    ាញ់
    0.48
    ਹ
    0.47
    lern
    0.47
    féle
    0.46
    litz
    0.46
    Estas
    0.45
    ᱠ
    0.44
    POSITIVE LOGITS
     kd
    0.47
     textarea
    0.47
     vùng
    0.46
     hearty
    0.46
    рма
    0.46
     забе
    0.46
     كلمة
    0.45
    textArea
    0.45
     впечатление
    0.44
     TextArea
    0.43
    Activations Density 0.000%

    No Known Activations