© 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. 79845
    Prev
    Next
    INDEX
    Explanations

    choosing or refusing options

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

    cannot override instructions

    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
    ু
    0.57
    u
    0.52
     FTX
    0.49
    را
    0.49
    ون
    0.48
    স্ক
    0.48
    LOS
    0.47
    ط
    0.47
    ع
    0.47
    your
    0.45
    POSITIVE LOGITS
    Lycodon
    0.44
     사인
    0.42
    𝑓
    0.40
     lends
    0.40
     세제곱
    0.40
    ;'
    0.40
     supple
    0.40
     immunoglobulin
    0.38
     причин
    0.38
     нә
    0.38
    Activations Density 0.000%

    No Known Activations