© 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-65K
    7. 41010
    Prev
    Next
    INDEX
    Explanations

    explains technical or conceptual distinctions

    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_65k_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
     выступа
    0.45
    くなる
    0.43
                    
    0.41
     самостоя
    0.41
    0.40
     troubled
    0.40
     SPIN
    0.39
    뗄
    0.39
    gence
    0.38
     ﷺ
    0.38
    POSITIVE LOGITS
    த்த
    0.48
    юд
    0.46
    áló
    0.46
    ည
    0.46
    бро
    0.45
    陈
    0.45
    户
    0.44
    芑
    0.43
    مال
    0.42
     preko
    0.41
    Activations Density 0.018%

    No Known Activations