© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 13280
    Prev
    Next
    INDEX
    Explanations

    forum threads started by

    np_acts-logits-general · gemini-2.5-flash-lite

    forums and discussions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     endot
    0.45
     endothelium
    0.43
     albumin
    0.41
     hemoglobin
    0.41
     vocab
    0.40
     declinations
    0.40
     polysaccharide
    0.39
    澱
    0.39
     kinases
    0.39
     denaturation
    0.39
    POSITIVE LOGITS
    forums
    1.05
    论坛
    1.02
     фору
    0.98
     forum
    0.98
     форум
    0.97
    forum
    0.95
     forums
    0.90
    Forum
    0.90
    showthread
    0.90
     Forums
    0.88
    Activations Density 0.024%

    No Known Activations