© 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. 5231
    Prev
    Next
    INDEX
    Explanations

    predictive, generative, descriptive

    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
    elab
    2.09
    eward
    2.06
     confund
    2.03
     exchangers
    1.93
    åd
    1.89
    taobao
    1.88
     listopadu
    1.87
    陞
    1.87
    erp
    1.79
    zhou
    1.79
    POSITIVE LOGITS
    features
    1.78
    ductory
    1.75
     factor
    1.66
     features
    1.60
    ive
    1.57
     spirit
    1.56
    IVE
    1.49
     Bowie
    1.47
     فعل
    1.47
     Feature
    1.44
    Activations Density 0.395%

    No Known Activations