© 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. 40-GEMMASCOPE-2-RES-262K
    7. 11515
    Prev
    Next
    INDEX
    Explanations

    formula for

    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_40_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
    jad
    0.41
     امی
    0.41
     создании
    0.40
    府
    0.39
     созда
    0.38
     न्यूमेरिकल
    0.38
    ᇂ
    0.37
     생성
    0.36
    jav
    0.36
    Sky
    0.36
    POSITIVE LOGITS
    ë
    0.50
     welche
    0.43
     derived
    0.41
     arba
    0.41
     k
    0.40
     ktorá
    0.39
    provided
    0.38
     reminiscent
    0.38
    ppery
    0.38
     inspired
    0.38
    Activations Density 0.002%

    No Known Activations