© 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-16K
    7. 10555
    Prev
    Next
    INDEX
    Explanations

    academic research topics and methods

    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_16k_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
    ྥ
    0.71
    ண்ட்
    0.68
    ных
    0.66
    美女
    0.66
    手
    0.64
    rik
    0.64
    pytorch
    0.63
    र्य
    0.62
    να
    0.61
    θα
    0.61
    POSITIVE LOGITS
    a
    0.82
     Research
    0.81
     araşt
    0.80
     research
    0.79
     as
    0.79
     in
    0.78
    RESEARCH
    0.76
    ال
    0.75
    ה
    0.75
     investigate
    0.73
    Activations Density 0.157%

    No Known Activations