© 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. 109141
    Prev
    Next
    INDEX
    Explanations

    after certain tokens

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

    Calvary Chapel

    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
    ขึ้น
    0.48
    ответ
    0.47
    谓
    0.45
    ผิด
    0.44
    에도
    0.44
    อ
    0.43
    กอง
    0.42
    אנ
    0.42
    喤
    0.42
    ยัง
    0.41
    POSITIVE LOGITS
     ज्वालामुखी
    0.54
     memories
    0.52
     digestive
    0.49
     paleont
    0.48
     reminis
    0.47
     detox
    0.47
     investigative
    0.46
     cancer
    0.46
     clues
    0.46
    yg
    0.46
    Activations Density 0.001%

    No Known Activations