© 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. 15459
    Prev
    Next
    INDEX
    Explanations

    various texts, media, and 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
     productores
    0.49
     miesto
    0.46
    本書
    0.45
     approche
    0.44
     निर्धारक
    0.44
    ኵ
    0.42
     impide
    0.42
     poursu
    0.42
     pré
    0.41
     expertos
    0.41
    POSITIVE LOGITS
    Various
    0.45
     Various
    0.44
     various
    0.43
     topics
    0.41
     많이
    0.41
     on
    0.40
     Pieces
    0.40
    유
    0.39
     रिलेटेड
    0.39
     వివిధ
    0.39
    Activations Density 0.021%

    No Known Activations