© 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. 166247
    Prev
    Next
    INDEX
    Explanations

    detailed unitwooden giftpolicy plan

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

    though often

    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
    ileri
    0.52
    uliert
    0.52
    leti
    0.51
    `${
    0.50
    ilian
    0.48
    ły
    0.48
    elessly
    0.47
     απε
    0.47
    。“
    0.46
    ۔
    0.45
    POSITIVE LOGITS
    꼰
    0.50
     Vorteil
    0.48
     Turnbull
    0.48
     карь
    0.46
    岘
    0.46
    独特
    0.46
    大丈夫
    0.44
     Experiences
    0.44
     עם
    0.44
    반
    0.43
    Activations Density 0.001%

    No Known Activations