© 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. 13985
    Prev
    Next
    INDEX
    Explanations

    as well

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

    addresses everyone or clipboard

    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
     hoặc
    0.40
    forums
    0.40
     oppure
    0.39
     Forums
    0.39
    েনে
    0.38
    )|
    0.38
     ود
    0.38
     или
    0.38
     forums
    0.38
    截至
    0.37
    POSITIVE LOGITS
     playfully
    0.51
    顧客
    0.48
    迎接
    0.46
    復活
    0.46
    กับการ
    0.46
    との
    0.46
    嘜
    0.45
     comedic
    0.44
    დესაც
    0.44
     принятия
    0.43
    Activations Density 0.000%

    No Known Activations