© 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. 77341
    Prev
    Next
    INDEX
    Explanations

    full page, maximize, fill

    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
     I
    0.45
     Á
    0.43
     ‘
    0.41
    itas
    0.41
     Philippine
    0.40
        
    0.40
     valor
    0.40
     TikTok
    0.39
     Xavier
    0.39
     suma
    0.39
    POSITIVE LOGITS
    LogRow
    0.44
    esehen
    0.44
    ревнова
    0.43
    uere
    0.42
    σιμοποι
    0.42
    倸
    0.42
    кте
    0.41
    ㄻ
    0.41
     נע
    0.41
    眹
    0.40
    Activations Density 0.001%

    No Known Activations