© 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. 7-GEMMASCOPE-2-RES-16K
    7. 14767
    Prev
    Next
    INDEX
    Explanations

    pero que

    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_7_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
    offs
    2.45
    ùi
    2.39
    '."
    2.37
    ''.
    2.36
    .''
    2.34
    .&
    2.30
     staffs
    2.30
     Bucc
    2.28
    Else
    2.28
    𝗻
    2.27
    POSITIVE LOGITS
    े
    3.12
    es
    3.12
    el
    3.04
    a
    3.03
    া
    3.02
    ার
    2.97
    aal
    2.93
    an
    2.81
    aar
    2.75
    ו
    2.70
    Activations Density 0.007%

    No Known Activations