© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 8608
    Prev
    Next
    INDEX
    Explanations

    intent, payload, recipient, sentiment, comedian

    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_262k_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
    {
    1.34
    การ
    1.28
     joten
    1.24
    𝐡
    1.22
    한
    1.21
    الم
    1.21
    一个
    1.19
    н
    1.17
    人気
    1.16
     besoin
    1.14
    POSITIVE LOGITS
    atilde
    1.39
    lerinden
    1.36
    dew
    1.36
     אשר
    1.32
    aud
    1.31
    findElements
    1.31
     voces
    1.30
     ות
    1.28
    sons
    1.28
    andte
    1.27
    Activations Density 0.027%

    No Known Activations