© 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. 73296
    Prev
    Next
    INDEX
    Explanations

    place names and religious texts

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

    asks for, means you

    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
     然而
    0.48
    電腦
    0.46
     azonban
    0.45
     tuttavia
    0.44
     however
    0.44
    然而
    0.44
    鰭
    0.43
    했지만
    0.43
     Toutefois
    0.43
    Однако
    0.43
    POSITIVE LOGITS
     وق
    0.51
     изда
    0.49
    犷
    0.49
     おい
    0.48
     که
    0.47
     igual
    0.47
     الس
    0.46
     कभी
    0.46
     दोषियों
    0.46
    しない
    0.46
    Activations Density 0.000%

    No Known Activations