© 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. 2293
    Prev
    Next
    INDEX
    Explanations

    borders and limits

    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
    ал
    2.37
    ы
    2.25
    राज्य
    2.23
    \{
    2.04
    ati
    2.01
     riser
    2.01
    ید
    1.99
    ետ
    1.96
    λεσμα
    1.92
     kunci
    1.90
    POSITIVE LOGITS
    緣
    2.84
    เขต
    2.50
    𝑵
    2.48
     localidades
    2.43
    陲
    2.42
     solcher
    2.41
     delim
    2.40
     confining
    2.40
    geoType
    2.40
    나가
    2.38
    Activations Density 0.228%

    No Known Activations