© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 11367
    Prev
    Next
    INDEX
    Explanations

    technical world realism

    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_13_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
    علم
    1.26
    ussy
    1.14
    uigen
    1.12
    an
    1.10
    incision
    1.09
    u
    1.09
    مال
    1.09
    urados
    1.07
    לית
    1.07
    iders
    1.06
    POSITIVE LOGITS
    相關
    1.76
     Related
    1.72
    <unused2140>
    1.63
     kapcsol
    1.61
     বৃদ্ধি
    1.59
    相关的
    1.58
     관련된
    1.55
    関連
    1.55
    
    1.55
     Đây
    1.54
    Activations Density 0.000%

    No Known Activations