© 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-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 2422
    Prev
    Next
    INDEX
    Explanations

    compound terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_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
    ם
    1.31
    க்
    1.17
    นาย
    1.07
    اں
    1.00
    lah
    0.98
    ことができる
    0.93
    თან
    0.92
    sy
    0.92
    ei
    0.91
    ದ
    0.91
    POSITIVE LOGITS
    깐
    1.58
    pper
    1.31
    xtures
    1.24
    ñas
    1.23
    ño
    1.21
    ョ
    1.16
    pped
    1.16
    ppu
    1.15
    ệt
    1.15
    pping
    1.15
    Activations Density 0.282%

    No Known Activations