© 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. 208495
    Prev
    Next
    INDEX
    Explanations

    like this

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

    payment made

    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
     grinder
    0.50
     napkins
    0.47
     incompressible
    0.46
     secondes
    0.46
     teamwork
    0.46
     apar
    0.45
     skyscrapers
    0.45
     গ
    0.44
     dood
    0.44
     insurmountable
    0.44
    POSITIVE LOGITS
    ϛ
    0.44
    었고
    0.42
    わけ
    0.40
    polymer
    0.39
    vartheta
    0.39
    this
    0.38
     факт
    0.38
    十六
    0.38
    органи
    0.38
    зы
    0.37
    Activations Density 0.001%

    No Known Activations