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

    Neuronpedia

    Jacobian LensNEW
    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. 63765
    Prev
    Next
    INDEX
    Explanations

    saying things or explaining topics

    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
    0.50
    \|$.
    0.46
    hmann
    0.43
    $.
    0.43
     ELEMENTS
    0.42
    :.
    0.41
    COTT
    0.41
       
    0.40
    Toe
    0.40
    䇝
    0.39
    POSITIVE LOGITS
     கூறி
    0.54
    告訴
    0.52
     nghĩ
    0.51
     powied
    0.50
     nói
    0.50
    라는
    0.49
     opção
    0.48
     kaže
    0.48
     mengatakan
    0.47
     сообщает
    0.47
    Activations Density 0.004%

    No Known Activations