© 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. 13-GEMMASCOPE-2-RES-16K
    7. 7900
    Prev
    Next
    INDEX
    Explanations

    Trump Administration, ice sprite

    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
    ยัง
    1.56
     심
    1.55
    ъем
    1.49
     다양
    1.42
    mov
    1.40
     실
    1.38
     와
    1.37
     긴
    1.37
    빵
    1.37
    MAPb
    1.37
    POSITIVE LOGITS
     logique
    1.46
     log
    1.41
    acon
    1.41
    Errors
    1.41
    enemy
    1.39
    ঘ্র
    1.37
     cité
    1.37
     insinu
    1.36
     ideales
    1.34
     canalicul
    1.33
    Activations Density 0.000%

    No Known Activations