© 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. 45038
    Prev
    Next
    INDEX
    Explanations

    specific items followed by context

    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
    വിധ
    0.42
     isang
    0.41
    मेलन
    0.41
     oznacza
    0.40
     首先
    0.39
     extraordinaire
    0.39
     either
    0.39
    ن
    0.39
    有一种
    0.38
     comunic
    0.38
    POSITIVE LOGITS
    ၜ
    0.41
     Geträn
    0.38
     суу
    0.38
     акча
    0.37
    ؎
    0.37
    諺
    0.37
     Wheeler
    0.36
     টাকার
    0.36
    苣
    0.35
     lipstick
    0.35
    Activations Density 0.052%

    No Known Activations