© 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. 162982
    Prev
    Next
    INDEX
    Explanations

    bathrooms and made without

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

    algorithms, statistical probabilities, generating text

    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
     high
    0.51
     March
    0.48
     Jed
    0.48
     High
    0.48
     H
    0.46
     G
    0.46
    ↵
    0.46
     B
    0.46
     F
    0.46
     Public
    0.46
    POSITIVE LOGITS
    霟
    0.58
    語言
    0.56
    𝘴
    0.55
    Автор
    0.54
    讓我
    0.53
    给我
    0.53
    Ссылка
    0.53
    анали
    0.53
    Ⲁ
    0.52
     парази
    0.52
    Activations Density 0.000%

    No Known Activations