© 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. 126878
    Prev
    Next
    INDEX
    Explanations

    sagging things; cramped quarters

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

    impact, presence, recommend, weight

    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
     consomm
    0.51
     achat
    0.49
     substrates
    0.47
     biochem
    0.46
    一
    0.44
     imports
    0.43
     importer
    0.43
     sparing
    0.43
     sands
    0.43
     producent
    0.43
    POSITIVE LOGITS
     pidió
    0.57
     celebró
    0.53
     salió
    0.53
     quedó
    0.50
     関係
    0.50
     resultó
    0.48
     llegó
    0.48
    ̂
    0.48
     quería
    0.48
     falleció
    0.47
    Activations Density 0.001%

    No Known Activations