© 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. 239897
    Prev
    Next
    INDEX
    Explanations

    location details and entities

    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
    arono
    0.59
     bzw
    0.57
     அல்லது
    0.53
     erfolgte
    0.51
    é
    0.50
     혹은
    0.50
    SetValue
    0.49
    dır
    0.49
     veya
    0.48
     effettu
    0.48
    POSITIVE LOGITS
     equities
    0.55
     briefings
    0.47
     Reuters
    0.46
     searing
    0.45
     President
    0.43
     Estonia
    0.43
     thermoplastics
    0.43
    獲
    0.43
    鏑
    0.43
     equity
    0.42
    Activations Density 0.002%

    No Known Activations