© 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
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-65K
    4. 357
    Prev
    Next
    INDEX
    Explanations

    english wikipedia references

    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
     Z
    1.07
     U
    1.06
     J
    0.99
     Common
    0.96
     korist
    0.96
     ogen
    0.95
     Must
    0.94
    Z
    0.94
     golden
    0.94
    U
    0.93
    POSITIVE LOGITS
    rance
    1.58
    volvimento
    1.53
    raded
    1.46
    ensione
    1.45
    ựa
    1.45
    theless
    1.43
    ignement
    1.43
    namese
    1.42
    ricing
    1.41
    érance
    1.41
    Activations Density 0.131%

    No Known Activations