© 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. 58
    Prev
    Next
    INDEX
    Explanations

    health monitoring; communities

    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
     essi
    0.91
     assaulted
    0.89
     hesit
    0.88
    ni
    0.88
    teste
    0.88
    IN
    0.87
    ri
    0.86
    ক
    0.86
     polled
    0.86
    }°
    0.84
    POSITIVE LOGITS
     Гос
    0.95
    Serializable
    0.85
    。
    0.84
    ными
    0.83
     Recipe
    0.83
     Helper
    0.83
     Resonance
    0.82
     Majorana
    0.82
     PRS
    0.82
     Resource
    0.81
    Activations Density 0.000%

    No Known Activations