© 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. 142217
    Prev
    Next
    INDEX
    Explanations

    Pot Shells

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

    recipient, competition, frustrated

    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
     нис
    0.48
     재
    0.44
    后缀
    0.44
     이제
    0.44
     मास
    0.44
    otipos
    0.43
    왼
    0.43
     катего
    0.42
    各式
    0.42
     퇴
    0.42
    POSITIVE LOGITS
    RY
    0.52
     krijg
    0.50
     enkel
    0.50
     lima
    0.49
    uj
    0.49
     York
    0.47
     metri
    0.46
     williams
    0.46
     discussing
    0.46
     arma
    0.45
    Activations Density 0.000%

    No Known Activations