© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 29999
    Prev
    Next
    INDEX
    Explanations

    technical and language concepts

    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
    ut
    0.80
    ab
    0.69
    un
    0.68
    can
    0.63
    d
    0.61
    ul
    0.59
    ang
    0.57
    ger
    0.56
    c
    0.56
     can
    0.55
    POSITIVE LOGITS
    ன்
    0.63
     писа
    0.63
    ל
    0.62
    า
    0.61
     reshaping
    0.59
     G
    0.57
    भीर
    0.55
    ्यारह
    0.55
    渦
    0.55
    リー
    0.54
    Activations Density 0.725%

    No Known Activations