© 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. 245304
    Prev
    Next
    INDEX
    Explanations

    father, siblings, playing roles

    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
    น้ำ
    0.48
    猚
    0.47
    ได้รับ
    0.43
    เพื่อให้
    0.43
    รับ
    0.42
    น่า
    0.42
     получен
    0.42
     ricevuto
    0.42
     Adapun
    0.41
    👷
    0.41
    POSITIVE LOGITS
     familial
    0.46
     compromising
    0.45
     siblings
    0.43
     weaning
    0.41
     sensitively
    0.41
     sisters
    0.41
     migr
    0.41
    griffen
    0.41
     fluidity
    0.41
    siblings
    0.41
    Activations Density 0.001%

    No Known Activations