© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 13496
    Prev
    Next
    INDEX
    Explanations

    transition and structural failures

    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
    microphone
    1.60
     txtbtn
    1.58
     contrats
    1.57
    themed
    1.56
    𝐲
    1.56
    newTask
    1.54
     taches
    1.53
    ्‍यादा
    1.52
    signup
    1.50
    𝕦
    1.47
    POSITIVE LOGITS
     (
    1.17
    ి
    1.15
    htar
    1.15
     وا
    1.12
    -
    1.03
    أ
    1.03
     لا
    1.00
     أحد
    1.00
    ء
    0.98
     اند
    0.97
    Activations Density 0.000%

    No Known Activations