© 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. 7-GEMMASCOPE-2-RES-16K
    7. 11388
    Prev
    Next
    INDEX
    Explanations

    Al- prefixes

    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
     randomNumber
    2.18
     rho
    2.14
     sóng
    2.08
    卿
    2.07
    وسک
    2.07
     io
    2.05
    輿
    1.98
    ᅧ
    1.94
    你
    1.94
     फिगर
    1.92
    POSITIVE LOGITS
    reise
    2.05
     હત્યા
    1.90
    nogo
    1.84
     hars
    1.82
    ambat
    1.82
    ის
    1.79
    राबरी
    1.79
    opent
    1.79
    汁
    1.78
    łos
    1.78
    Activations Density 0.016%

    No Known Activations