© 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
    2. Gemma-3-270M
    3. 12-GEMMASCOPE-2-RES-16K
    4. 6310
    Prev
    Next
    INDEX
    Explanations

    python class constructor

    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
     whereupon
    1.79
     though
    1.63
    though
    1.57
    闔
    1.54
     although
    1.52
    although
    1.50
     hvor
    1.49
     however
    1.48
     for
    1.43
    where
    1.41
    POSITIVE LOGITS
    =\"
    2.07
    UTRON
    1.91
    ASCADE
    1.84
    ="-
    1.78
     '@
    1.76
    )=(-
    1.75
    =='
    1.75
     multiplets
    1.74
    ylab
    1.71
    FERRED
    1.70
    Activations Density 0.000%

    No Known Activations