© 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. 132869
    Prev
    Next
    INDEX
    Explanations

    professions and specific entities

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

    interfaces and integrations

    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
    י
    0.50
    ,
    0.49
    ی
    0.48
    ουλ
    0.47
    ές
    0.45
     doct
    0.44
    채
    0.44
    رر
    0.44
    我会
    0.43
    یی
    0.43
    POSITIVE LOGITS
     電力
    0.50
     Eigen
    0.46
     Emmy
    0.46
     ट्रांसपोर्ट
    0.46
     Chopin
    0.45
     മറ്റ്
    0.45
     শিগ
    0.44
    ime
    0.44
     സ്വന്ത
    0.43
     private
    0.43
    Activations Density 0.000%

    No Known Activations