© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 166756
    Prev
    Next
    INDEX
    Explanations

    visiting places, events, or family

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

    zero-shot generalization

    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
    Negative Logits
     Optics
    0.52
     第三
    0.49
    ૩
    0.47
    getTarget
    0.46
     ঘ
    0.45
    关系
    0.44
    ewidth
    0.44
    idemargin
    0.43
    关系的
    0.43
    ervices
    0.43
    POSITIVE LOGITS
    ና
    0.48
    供應
    0.48
    ]."
    0.48
    damn
    0.46
    junctive
    0.46
    क्के
    0.46
    紛
    0.46
     inconvenient
    0.45
    出荷
    0.45
     numer
    0.45
    Activations Density 0.000%

    No Known Activations