© 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. 4819
    Prev
    Next
    INDEX
    Explanations

    command-line tools

    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
     cobbled
    1.54
    UIColor
    1.49
    msgs
    1.34
    mē
    1.30
     autón
    1.27
     Alberts
    1.27
    äch
    1.24
    간
    1.23
    inya
    1.23
    shire
    1.22
    POSITIVE LOGITS
    قتص
    1.86
    AutoSize
    1.80
    岖
    1.67
     Продол
    1.65
     јуну
    1.63
    حث
    1.58
    єм
    1.56
     מיט
    1.54
    协商
    1.54
     Ranking
    1.51
    Activations Density 0.007%

    No Known Activations