© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 7694
    Prev
    Next
    INDEX
    Explanations

    helping businesses

    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
    নি
    1.30
    ⊆
    1.26
    ﻦ
    1.18
    inku
    1.09
    لاھ
    1.08
     CCOC
    1.07
    ිනි
    1.07
     मनी
    1.06
    🧩
    1.05
    琴
    1.05
    POSITIVE LOGITS
     hinch
    1.14
     conspicuous
    1.14
     aurait
    1.13
     brag
    1.06
     humiliated
    1.05
     disgraced
    1.04
    o
    1.01
     large
    1.00
     exploding
    0.99
     gast
    0.99
    Activations Density 0.000%

    No Known Activations