© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 1232
    Prev
    Next
    INDEX
    Explanations

    introducing comparison tables

    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_65k_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
    u
    1.06
    y
    0.96
    en
    0.91
    e
    0.90
    i
    0.82
    a
    0.79
    o
    0.78
     U
    0.78
    er
    0.77
     …
    0.76
    POSITIVE LOGITS
    ExpNow
    1.20
    NUCLEAR
    1.17
    Dragging
    1.14
    CORPOR
    1.12
    BySize
    1.11
    𝓗
    1.10
    NEUTRON
    1.09
    Bokeh
    1.09
    REACTOR
    1.09
    Nucle
    1.07
    Activations Density 0.259%

    No Known Activations