© 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. 239648
    Prev
    Next
    INDEX
    Explanations

    official parent companies

    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
    Church
    0.50
    O
    0.49
    צ
    0.49
    S
    0.48
    ط
    0.47
    叕
    0.46
    >{</
    0.46
    પણ
    0.46
    to
    0.45
    원의
    0.45
    POSITIVE LOGITS
     ponctués
    0.59
     impairs
    0.59
     پائی
    0.52
     provoked
    0.51
     stripped
    0.50
     perdida
    0.50
     ایڈ
    0.49
     alters
    0.48
     Parr
    0.48
     provoking
    0.47
    Activations Density 0.000%

    No Known Activations