© 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
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-65K
    4. 1259
    Prev
    Next
    INDEX
    Explanations

    as, comparison, or escalating scale

    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
    ebe
    1.13
    een
    1.10
    brow
    1.09
    lars
    1.09
    produkt
    1.04
    tura
    1.04
    xing
    1.02
    瑁
    1.00
    বন্ত
    1.00
    tors
    0.99
    POSITIVE LOGITS
     Tape
    1.31
     Grain
    1.29
     Def
    1.28
     tape
    1.26
     Jobs
    1.24
    Merc
    1.23
     Bond
    1.22
     Wages
    1.20
    Living
    1.18
    Jobs
    1.18
    Activations Density 0.027%

    No Known Activations