© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 170478
    Prev
    Next
    INDEX
    Explanations

    rampage continuing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    u
    0.45
     genitalia
    0.45
     unfortunate
    0.44
    ﻜ
    0.44
     ግን
    0.43
     Gren
    0.43
    桂
    0.43
    ﻞ
    0.43
     حسن
    0.42
     Lemb
    0.42
    POSITIVE LOGITS
     ફિલ્મ
    0.48
     kế
    0.46
    িলের
    0.45
     ještě
    0.45
     kvůli
    0.44
     영화
    0.43
     চলচ্চিত্রে
    0.43
    $&
    0.43
     चित्रपटा
    0.43
    //
    0.42
    Activations Density 0.001%

    No Known Activations