© 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. 13-GEMMASCOPE-2-RES-16K
    7. 12173
    Prev
    Next
    INDEX
    Explanations

    percentage of sales or revenue

    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_13_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
    뮤
    1.31
    꾹
    1.27
    góc
    1.27
    벍
    1.26
     Inhibition
    1.26
    崠
    1.25
    ୮
    1.24
     minuta
    1.23
    √(
    1.22
     recort
    1.21
    POSITIVE LOGITS
     are
    0.94
     honored
    0.93
     surges
    0.87
     fodder
    0.86
     fx
    0.86
     privilege
    0.85
     says
    0.84
     v
    0.84
     Corridor
    0.83
     overflows
    0.81
    Activations Density 0.000%

    No Known Activations