© 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. 4531
    Prev
    Next
    INDEX
    Explanations

    actions, descriptions, or items

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

    "It" or "this" followed by a verb

    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
    json
    0.47
     首先
    0.45
     όλα
    0.45
     ()=>{
    0.44
    𝜃
    0.44
    mysqli
    0.43
     完全
    0.43
    INITIAL
    0.43
     开始
    0.43
    첫
    0.43
    POSITIVE LOGITS
     a
    0.50
     commenter
    0.49
     an
    0.49
     Garner
    0.48
     stewards
    0.47
     resists
    0.46
     commenters
    0.46
     Gunnar
    0.46
     Back
    0.46
     légère
    0.46
    Activations Density 0.000%

    No Known Activations