© 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. 342
    Prev
    Next
    INDEX
    Explanations

    lists or conditions for housing

    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
    كان
    0.91
    \}.
    0.87
    به
    0.86
    ي
    0.83
    رو
    0.80
    <0xB2>
    0.79
    ्यूशन
    0.79
    萨
    0.79
    hive
    0.78
    рав
    0.78
    POSITIVE LOGITS
     '
    0.82
     millimeters
    0.82
    ൃത്ത
    0.78
     Reyes
    0.76
    sd
    0.76
     Massacre
    0.76
    dra
    0.75
    seg
    0.74
     Atoms
    0.74
     minds
    0.73
    Activations Density 0.000%

    No Known Activations