© 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. 165976
    Prev
    Next
    INDEX
    Explanations

    unlimited, infinite

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

    political discourse

    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
    禄
    0.54
     interv
    0.53
    стре
    0.52
     réd
    0.52
     ascenso
    0.49
    ゼル
    0.49
     spost
    0.49
     malice
    0.47
     zaidi
    0.47
    строва
    0.47
    POSITIVE LOGITS
    ja
    0.46
     //$
    0.42
     TBS
    0.41
    royd
    0.41
    yn
    0.40
    ear
    0.40
    kn
    0.40
    하여
    0.40
     CSV
    0.40
     Offices
    0.40
    Activations Density 0.001%

    No Known Activations