© 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. 46686
    Prev
    Next
    INDEX
    Explanations

    conversations, heat, based, consensus, consistent, depending

    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
    sendKeys
    0.48
     nhập
    0.46
     Bhojpuri
    0.44
    حة
    0.44
    యి
    0.43
    ဗ
    0.43
     Magazines
    0.42
    搔
    0.42
     الو
    0.41
    টায়
    0.41
    POSITIVE LOGITS
    Oui
    0.53
    Zespół
    0.45
    İlk
    0.43
    Ꮀ
    0.42
    Avec
    0.42
    Ꮏ
    0.41
     boomerang
    0.41
    กระ
    0.41
     довго
    0.41
    Hướng
    0.41
    Activations Density 0.019%

    No Known Activations