© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 12-GEMMASCOPE-2-RES-16K
    7. 369
    Prev
    Next
    INDEX
    Explanations

    evidence of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_12_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
    d
    0.95
    g
    0.91
    سه
    0.83
    lera
    0.81
    س
    0.80
    ן
    0.80
    اش
    0.79
    dna
    0.79
    ד
    0.79
    n
    0.78
    POSITIVE LOGITS
     позднее
    1.11
     suficiente
    0.99
     желательно
    0.97
     тщательно
    0.95
     suficientes
    0.93
    যথ
    0.91
     ключе
    0.90
     зачем
    0.89
     berkualitas
    0.89
     permitido
    0.88
    Activations Density 0.000%

    No Known Activations