© 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. 165857
    Prev
    Next
    INDEX
    Explanations

    own or his

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

    ranging from to

    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
    外观
    0.46
    片
    0.45
     片
    0.44
     Oak
    0.44
     Publication
    0.44
    片的
    0.43
     Passenger
    0.43
     mcg
    0.43
     Machinery
    0.42
    铆
    0.42
    POSITIVE LOGITS
     prípade
    0.46
    𝙨
    0.45
     njegova
    0.44
     tlak
    0.44
     jego
    0.43
     его
    0.42
     njeg
    0.42
     priprav
    0.42
     který
    0.42
     numai
    0.42
    Activations Density 0.004%

    No Known Activations