© 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. 13-GEMMASCOPE-2-RES-65K
    7. 2537
    Prev
    Next
    INDEX
    Explanations

    2D surface, 3D image

    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_65k_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
     filtro
    1.02
    Filter
    1.00
     يكون
    0.97
     dito
    0.96
     linf
    0.95
    ฺ
    0.94
    ディション
    0.93
    ኩል
    0.92
    <td>
    0.92
     dicho
    0.90
    POSITIVE LOGITS
     ornamentation
    1.23
     Halloween
    1.16
     decorations
    1.12
     Homecoming
    1.11
     carvings
    1.11
     harvest
    1.11
     harvesting
    1.10
     hollow
    1.09
     artistry
    1.09
     clipart
    1.08
    Activations Density 0.002%

    No Known Activations