© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 221006
    Prev
    Next
    INDEX
    Explanations

    legal documents, Engineering, Oman tonight

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

    based on calculations or simulations

    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
    Negative Logits
     fdPar
    0.48
    ባ
    0.47
     کھل
    0.46
     முன்னணி
    0.46
     فيما
    0.45
     အမျိုး
    0.45
     };
    0.45
     !}\
    0.45
     محور
    0.44
     Frei
    0.44
    POSITIVE LOGITS
    君
    0.50
    uluh
    0.46
    ulie
    0.45
    akan
    0.44
    eku
    0.44
    ене
    0.44
    过去了
    0.44
    usal
    0.44
    efi
    0.43
    को
    0.43
    Activations Density 0.000%

    No Known Activations