© 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. 197241
    Prev
    Next
    INDEX
    Explanations

    Johnson & Johnson, company names

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

    online platforms, software, code

    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
     дра
    0.53
    ರವಾಗಿ
    0.50
    碐
    0.48
     растений
    0.47
    䂙
    0.47
     також
    0.47
     CCSDT
    0.47
    ᕈ
    0.46
    高齢
    0.46
     RCLCPP
    0.46
    POSITIVE LOGITS
    0.43
     og
    0.42
     Pamela
    0.42
    <0xA0>
    0.42
    eller
    0.41
    aly
    0.41
    သမ
    0.41
    很多
    0.40
    Pam
    0.39
     january
    0.39
    Activations Density 0.000%

    No Known Activations