© 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. 1065
    Prev
    Next
    INDEX
    Explanations

    generating code and text

    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
    itiv
    0.84
    iert
    0.78
    aient
    0.76
    iere
    0.76
     strike
    0.75
    u
    0.75
    uating
    0.74
     disc
    0.73
    i
    0.73
     BP
    0.71
    POSITIVE LOGITS
     verwendeten
    1.28
    inheritDoc
    1.27
    ∑</
    1.27
    tabPage
    1.21
     soport
    1.19
    Healthcare
    1.18
     mempert
    1.18
     بالټ
    1.18
     Mitgl
    1.17
     które
    1.17
    Activations Density 0.264%

    No Known Activations