© 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. 26135
    Prev
    Next
    INDEX
    Explanations

    a series

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

    sissy wife, freshman, chin

    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
    творе
    0.50
    삶
    0.44
    ﻧ
    0.44
    未来
    0.42
    OCC
    0.42
    긍
    0.40
    нци
    0.40
    umma
    0.39
    narr
    0.39
     define
    0.39
    POSITIVE LOGITS
    țit
    0.48
     अकॉर्डिंग
    0.47
     इकट्ठा
    0.45
    StudentRecord
    0.45
     Αυ
    0.44
    ıc
    0.44
    ุ
    0.44
    ্টা
    0.43
     डाइट
    0.43
     С
    0.43
    Activations Density 0.000%

    No Known Activations