© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 6722
    Prev
    Next
    INDEX
    Explanations

    but not, but also

    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_24_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
    い
    1.13
     Cint
    0.98
    라면
    0.96
    յան
    0.95
    ı
    0.88
    IA
    0.86
    お届け
    0.85
    ん
    0.84
    ного
    0.81
    まして
    0.81
    POSITIVE LOGITS
    termilk
    1.06
     volna
    0.92
    сибо
    0.89
    ה
    0.88
    eers
    0.86
     বিষয়ে
    0.85
     także
    0.83
     তবুও
    0.83
    ação
    0.82
     digress
    0.82
    Activations Density 0.157%

    No Known Activations