© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 89574
    Prev
    Next
    INDEX
    Explanations

    before or after specific nouns

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

    remove extraneous elements

    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
    Ꮆ
    0.53
    GoAbroad
    0.51
    Unser
    0.51
    Importance
    0.48
    agers
    0.47
    PhotoButton
    0.46
    Hur
    0.46
    掝
    0.46
    裟
    0.46
    ferences
    0.45
    POSITIVE LOGITS
     has
    0.50
     biti
    0.50
     hacks
    0.47
     quien
    0.47
     exclude
    0.46
     cria
    0.46
    .),
    0.45
     połą
    0.45
     product
    0.44
     hacker
    0.44
    Activations Density 0.001%

    No Known Activations