© 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-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 135
    Prev
    Next
    INDEX
    Explanations

    that some / the / a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_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
    ?
    0.38
    。
    0.38
    Then
    0.38
     そして
    0.37
    E
    0.37
    O
    0.36
    _
    0.35
    Manager
    0.35
    S
    0.35
    M
    0.35
    POSITIVE LOGITS
     there
    0.81
     it
    0.63
    there
    0.62
     nobody
    0.57
     everyone
    0.54
     they
    0.54
     هناك
    0.54
     pessoas
    0.54
     we
    0.52
     jeder
    0.52
    Activations Density 1.119%

    No Known Activations