© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 1409
    Prev
    Next
    INDEX
    Explanations

    names followed by identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_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
    ्स
    1.09
    sic
    1.07
    ら
    1.04
    oretically
    1.04
    পক্ষে
    1.02
    앓
    0.99
    िफिशियल
    0.97
    と
    0.97
     কারণেই
    0.96
     নিজেও
    0.95
    POSITIVE LOGITS
     Под
    1.28
     Beratung
    1.27
     внед
    1.25
     Angular
    1.23
     proficient
    1.21
     algéb
    1.21
     tional
    1.20
     ПО
    1.20
     Stevie
    1.20
     Anwendung
    1.20
    Activations Density 0.040%

    No Known Activations