© 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. 121401
    Prev
    Next
    INDEX
    Explanations

    ownership, or terms

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

    skilled practitioner, copper tape, network segment

    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
    ুল্য
    0.49
    ート
    0.47
     코로나
    0.45
    нима
    0.45
    ື່
    0.45
    ி
    0.44
     comprobar
    0.44
    ᱘
    0.43
    pandemic
    0.43
     कोरोनावायरस
    0.43
    POSITIVE LOGITS
    (
    0.46
    enzie
    0.45
    {
    0.45
     Angriff
    0.43
     tob
    0.42
     Gruber
    0.42
    coln
    0.42
    ্ধু
    0.42
     الكامل
    0.42
    萛
    0.42
    Activations Density 0.001%

    No Known Activations