© 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. 171
    Prev
    Next
    INDEX
    Explanations

    which followed by a verb

    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
    𝘦
    1.10
    ар
    1.03
    э
    1.02
     the
    1.01
     a
    1.00
    },
    0.99
    вропей
    0.97
     an
    0.97
    er
    0.95
    ي
    0.94
    POSITIVE LOGITS
    omethyl
    1.03
     касается
    0.97
     والذي
    0.96
    koľ
    0.94
    著名的
    0.94
    soever
    0.93
     والتي
    0.93
    ≳
    0.91
     Kondo
    0.91
     কিনা
    0.90
    Activations Density 1.059%

    No Known Activations