© 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. 229082
    Prev
    Next
    INDEX
    Explanations

    strong collectible, working with, certain products

    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
    ম্ভীর
    0.54
     directorio
    0.52
     humild
    0.49
    ্যাস
    0.48
     uname
    0.48
    娆
    0.47
     às
    0.46
    replic
    0.46
     kính
    0.46
    серед
    0.46
    POSITIVE LOGITS
    I
    0.51
     জরিমানা
    0.50
    Loren
    0.43
    tage
    0.43
    Reduced
    0.43
    จำนวน
    0.42
    o
    0.42
    eing
    0.42
    kennung
    0.41
    貶
    0.41
    Activations Density 0.001%

    No Known Activations