© 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. 98477
    Prev
    Next
    INDEX
    Explanations

    political operationqualified for officedifficult for shopperslanguage as toolland than grainNotice how variables

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

    land reclamation

    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
     วัด
    0.53
     útiles
    0.49
     ஆகிய
    0.43
     также
    0.42
    árl
    0.42
     Collaborative
    0.42
     гэта
    0.42
     天
    0.41
     ஆகியவற்ற
    0.41
     फार्
    0.41
    POSITIVE LOGITS
     প্রচারণা
    0.49
     perintah
    0.48
     regain
    0.46
    GetWidth
    0.44
     প্রচ
    0.44
    తోంది
    0.43
    原型
    0.43
    廠
    0.42
    מצע
    0.42
    резать
    0.42
    Activations Density 0.001%

    No Known Activations