© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 7327
    Prev
    Next
    INDEX
    Explanations

    project or effort involving

    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
     focus
    0.88
    alo
    0.87
    ptide
    0.85
    올
    0.85
     foci
    0.84
     resumption
    0.83
     concentrate
    0.83
    팬
    0.82
     যেন
    0.81
    فع
    0.80
    POSITIVE LOGITS
     led
    2.54
     sponsored
    1.99
     Led
    1.86
     spearheaded
    1.85
    Led
    1.84
     coached
    1.82
     managed
    1.76
     hosted
    1.76
     controlled
    1.74
     owned
    1.73
    Activations Density 0.214%

    No Known Activations