© 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. 157414
    Prev
    Next
    INDEX
    Explanations

    interact with

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

    interact and interactive

    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
    ו
    0.66
    Е
    0.61
     volunte
    0.60
    inę
    0.57
     おい
    0.55
    А
    0.55
    است
    0.52
    뉩
    0.52
     unchallenged
    0.52
    の説明
    0.52
    POSITIVE LOGITS
     взаимодействия
    1.24
    互動
    1.21
    Interact
    1.16
     interact
    1.15
     Interactions
    1.15
    互动
    1.11
     взаимодействие
    1.10
     Interact
    1.09
     Interaction
    1.08
     interaction
    1.06
    Activations Density 0.040%

    No Known Activations