© 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-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 9037
    Prev
    Next
    INDEX
    Explanations

    Arranging and aligning elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_22_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
    劍
    1.01
     electrochemical
    0.96
    xhr
    0.95
     CDI
    0.91
     viper
    0.90
     elec
    0.89
     Heater
    0.86
    읊
    0.86
     thermocouple
    0.84
     Polize
    0.83
    POSITIVE LOGITS
     alignment
    1.65
     Alignment
    1.62
    alignment
    1.61
     aligning
    1.59
    align
    1.57
    Alignment
    1.56
     alignments
    1.55
     align
    1.51
     aligned
    1.50
    Align
    1.49
    Activations Density 0.233%

    No Known Activations