© 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. 139440
    Prev
    Next
    INDEX
    Explanations

    patent application identifiers

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

    US and IE patent documents

    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
    暊
    0.50
     Gmail
    0.48
     FIFA
    0.47
     पैदल
    0.47
     CpG
    0.47
    㸽
    0.46
     اعلام
    0.46
    呫
    0.45
    㷅
    0.45
    誕生日
    0.44
    POSITIVE LOGITS
    E
    0.52
    +')
    0.51
    K
    0.47
    A
    0.46
    ZI
    0.46
    Fact
    0.45
    Quant
    0.45
    Indent
    0.44
     literat
    0.44
    Published
    0.44
    Activations Density 0.003%

    No Known Activations