© 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. 122821
    Prev
    Next
    INDEX
    Explanations

    various followed by election, necessary followed by to, exclusive followed by rights

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

    remarkably or interfering with

    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
    琪
    0.49
    risk
    0.46
    बल
    0.46
    危険
    0.46
    ່ນ
    0.46
    AIS
    0.46
    遊
    0.45
    リスク
    0.44
    力
    0.44
    뷰
    0.44
    POSITIVE LOGITS
     లేదా
    0.49
     formule
    0.47
     abhid
    0.47
     अंगों
    0.46
     அல்லது
    0.45
     Honour
    0.45
    ্রেট
    0.45
     десять
    0.44
     decreto
    0.44
     ভাগে
    0.44
    Activations Density 0.000%

    No Known Activations