© 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. 203486
    Prev
    Next
    INDEX
    Explanations

    thread wearssignifies thatfirst childenabled mobileConsequently, knowing

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

    writer's crew

    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
    usun
    0.58
     寝
    0.54
     這
    0.53
     들어
    0.52
     場所
    0.52
     保護
    0.52
     vào
    0.49
     気
    0.48
     乾燥
    0.48
     組
    0.47
    POSITIVE LOGITS
     bounced
    0.50
    Operation
    0.41
    Initi
    0.41
    离婚
    0.41
    vous
    0.40
     Subsequent
    0.39
     dépassant
    0.39
    Magn
    0.38
    怿
    0.38
     recorded
    0.38
    Activations Density 0.005%

    No Known Activations