© 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. 4153
    Prev
    Next
    INDEX
    Explanations

    developing

    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
    8
    0.95
    7
    0.93
    6
    0.91
    1
    0.84
    4
    0.83
     Германия
    0.74
    IE
    0.73
    .
    0.71
    </h3>
    0.68
    5
    0.66
    POSITIVE LOGITS
    develop
    0.94
     Developed
    0.92
     Develop
    0.91
    ق
    0.90
    Develop
    0.84
     entwick
    0.84
    developed
    0.84
    h
    0.84
     desenvolv
    0.83
    DEVELOP
    0.81
    Activations Density 0.125%

    No Known Activations