© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 24597
    Prev
    Next
    INDEX
    Explanations

    abstract descriptions

    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
     President
    0.39
     Aj
    0.39
     Sk
    0.37
    炊
    0.36
     Te
    0.36
     Co
    0.35
    8
    0.35
     Uk
    0.34
     Deleg
    0.34
    7
    0.34
    POSITIVE LOGITS
    вор
    0.41
     soulful
    0.41
    성과
    0.40
     глубо
    0.39
     기본적인
    0.39
    InfoWindow
    0.39
    तीत
    0.38
     естественно
    0.38
    чин
    0.38
    нюю
    0.38
    Activations Density 0.021%

    No Known Activations