© 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-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 4378
    Prev
    Next
    INDEX
    Explanations

    past tense verbs linking concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Binance
    1.26
    TikTok
    1.22
     TikTok
    1.21
     tiktok
    1.13
    Instagram
    1.13
     aktuell
    1.12
    Blockchain
    1.10
    <0xF3>
    1.10
     blockchain
    1.09
    িয়েছে
    1.09
    POSITIVE LOGITS
     was
    1.75
     وكانت
    1.64
     وكان
    1.50
     were
    1.48
    was
    1.38
    當時
    1.38
    当时的
    1.32
     Was
    1.31
     তখনকার
    1.30
     became
    1.26
    Activations Density 1.166%

    No Known Activations