© 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. 80995
    Prev
    Next
    INDEX
    Explanations

    Tamil, Vietnamese, French, Marathi, Romanian, Turkish, Chinese

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

    states and abstract concepts

    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
     smiled
    0.47
     showrooms
    0.47
     borderWidth
    0.46
     grilling
    0.46
     invading
    0.46
     traded
    0.45
     accredited
    0.44
    ୌ
    0.44
    琇
    0.44
    Makeup
    0.43
    POSITIVE LOGITS
     मिळेल
    0.49
     Truy
    0.49
     Sử
    0.48
    ச்
    0.48
     déclaration
    0.47
     சுய
    0.47
     Trebuie
    0.46
     Erişim
    0.46
     生命
    0.45
    睨
    0.45
    Activations Density 0.000%

    No Known Activations