© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 4260
    Prev
    Next
    INDEX
    Explanations

    of the

    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_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
     сбор
    1.10
     এরই
    1.03
     initComponents
    0.98
    끼
    0.97
     zaken
    0.97
    ッセージ
    0.96
     horizons
    0.96
    acyjnego
    0.96
    俑
    0.96
    odings
    0.93
    POSITIVE LOGITS
    sn
    1.42
     crappy
    1.33
     fatty
    1.32
     asshole
    1.28
    nm
    1.28
     screamed
    1.20
     shitty
    1.18
    nM
    1.18
    超級
    1.18
    めっちゃ
    1.17
    Activations Density 0.118%

    No Known Activations