© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 6229
    Prev
    Next
    INDEX
    Explanations

    quality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-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
     VIAF
    1.81
     dwar
    1.79
     MetaMask
    1.72
     inapplicable
    1.72
     asteroid
    1.68
    ɯ
    1.67
     lobbying
    1.67
    Trib
    1.65
    抬
    1.64
     hashtags
    1.63
    POSITIVE LOGITS
     Quality
    2.74
    Quality
    2.57
     quality
    2.31
    quality
    2.30
     QUALITY
    2.23
     kvalitet
    2.12
     품질
    2.00
    QC
    1.96
     qualidade
    1.94
    QUALITY
    1.94
    Activations Density 0.069%

    No Known Activations