© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 99642
    Prev
    Next
    INDEX
    Explanations

    repair, Francis, cash, prayer

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

    create rule page

    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
    ᱗
    0.50
     handelt
    0.50
    żenia
    0.49
    increases
    0.48
    ুকে
    0.48
    ѓ
    0.48
    ᱕
    0.48
    ethe
    0.47
    ак
    0.47
    ᱪ
    0.47
    POSITIVE LOGITS
    ts
    0.52
    แจ
    0.47
    濑
    0.46
    讓人
    0.45
    撈
    0.45
    捞
    0.44
     आराधना
    0.43
    一种
    0.41
    两次
    0.41
    Harvey
    0.41
    Activations Density 0.000%

    No Known Activations