© 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. 9350
    Prev
    Next
    INDEX
    Explanations

    brand names in consumer goods

    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
    rotechn
    0.82
     prox
    0.82
    脛
    0.81
    ovariant
    0.81
     extruded
    0.80
    SSF
    0.78
    arrange
    0.77
    weave
    0.77
     curled
    0.75
    粕
    0.74
    POSITIVE LOGITS
     Strad
    0.91
     பிள்ள
    0.91
     Peut
    0.89
     asignatura
    0.89
     Guess
    0.87
    GAP
    0.86
    產生
    0.86
     undeveloped
    0.85
     Bers
    0.83
    ﯼ
    0.83
    Activations Density 0.141%

    No Known Activations