© 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. 1208
    Prev
    Next
    INDEX
    Explanations

    help me tailor

    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
    ంటి
    2.32
    ์
    2.18
    ায়
    2.16
    蚱
    2.07
     महासचिव
    2.06
     internally
    2.03
    राण
    2.03
    増や
    2.01
    OPERATION
    2.01
    TimeUnit
    2.00
    POSITIVE LOGITS
    <bos>
    3.18
     entgegen
    2.14
    ब्दिक
    2.12
    고사
    2.12
    땄
    2.11
     quo
    2.09
    ر
    2.08
    แหน่ง
    2.02
    üllen
    2.01
    忑
    2.00
    Activations Density 0.375%

    No Known Activations