© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 12838
    Prev
    Next
    INDEX
    Explanations

    predicate triplets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_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
    흘
    1.44
    QUARE
    1.40
    ยืน
    1.34
    ளின்
    1.33
     altın
    1.25
     fühlen
    1.23
    祖
    1.23
    。。
    1.23
    ப்பே
    1.22
    angkah
    1.22
    POSITIVE LOGITS
     unwarrant
    1.69
     looming
    1.67
     propagand
    1.59
     rackets
    1.58
    िल्‍ली
    1.54
     extravag
    1.50
     haphazard
    1.50
     inco
    1.49
     exquisitely
    1.49
    phant
    1.49
    Activations Density 0.000%

    No Known Activations