© 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. 7-GEMMASCOPE-2-RES-16K
    7. 12216
    Prev
    Next
    INDEX
    Explanations

    roman numeral i

    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_7_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
    BorderStyle
    2.46
    erad
    2.41
     खड़ा
    2.29
    getRed
    2.18
    လမ်း
    2.12
    льного
    2.09
    iennes
    2.05
    ᓂ
    2.04
     surpr
    2.02
    ulin
    2.02
    POSITIVE LOGITS
    weights
    2.25
     weighed
    2.18
     weighing
    2.15
    weight
    2.10
     weight
    1.99
     tweezers
    1.98
    uttu
    1.96
     Weigh
    1.95
    WEIGHT
    1.90
     weights
    1.90
    Activations Density 0.034%

    No Known Activations