© 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. 8432
    Prev
    Next
    INDEX
    Explanations

    places and concepts in the world

    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
     outset
    0.39
     protagon
    0.37
    dq
    0.37
     GROUP
    0.36
    developer
    0.36
     {
    0.35
    enaar
    0.35
     suspect
    0.35
    noun
    0.34
    %)
    0.34
    POSITIVE LOGITS
     galleries
    0.47
    сная
    0.44
     wilds
    0.42
    棦
    0.42
    महा
    0.41
    मधील
    0.41
     şehir
    0.41
     bords
    0.41
    世界上最大的
    0.41
     forêt
    0.41
    Activations Density 0.084%

    No Known Activations