© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 50439
    Prev
    Next
    INDEX
    Explanations

    label:Project:feta-like cheese.surprises visitors

    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_262k_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
    sqcup
    0.48
    โ
    0.48
    publication
    0.46
    ப
    0.46
    ز
    0.46
    thirty
    0.45
     جریان
    0.45
    トー
    0.44
     publicação
    0.44
    ش
    0.43
    POSITIVE LOGITS
     overlays
    0.51
     attend
    0.51
     slaves
    0.50
     brane
    0.48
     plugins
    0.46
     surfactants
    0.46
     leaves
    0.45
     invariants
    0.45
     locus
    0.44
    Been
    0.44
    Activations Density 0.001%

    No Known Activations