© 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. 13-GEMMASCOPE-2-RES-16K
    7. 13852
    Prev
    Next
    INDEX
    Explanations

    Massive Dataset

    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
    enek
    1.35
    adlo
    1.29
    atial
    1.28
     grada
    1.28
    𝙞
    1.27
    instit
    1.27
    iterate
    1.25
    <unused308>
    1.25
    အတ
    1.24
    जग
    1.24
    POSITIVE LOGITS
     Bonnet
    1.22
    ↵
    1.21
     брать
    1.18
     Chávez
    1.14
     División
    1.13
     Sain
    1.10
     Cristó
    1.10
     chắn
    1.09
    line
    1.08
     Force
    1.05
    Activations Density 0.000%

    No Known Activations