© 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. 108
    Prev
    Next
    INDEX
    Explanations

    cheer

    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
    0
    1.19
    8
    1.15
    2
    1.10
    4
    1.05
    6
    1.05
    7
    1.02
    1
    1.02
    5
    1.00
    с
    0.97
    3
    0.96
    POSITIVE LOGITS
    ições
    1.09
    ीकरण
    1.09
    ಿಗಳ
    1.04
    لين
    0.97
    ו
    0.92
    ॉन
    0.89
    fdPar
    0.88
    iencia
    0.88
    ição
    0.87
     الدوري
    0.87
    Activations Density 0.000%

    No Known Activations