© 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-262K
    7. 11108
    Prev
    Next
    INDEX
    Explanations

    sets of four

    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
    து
    1.68
    𝗻
    1.59
    韓
    1.51
     dozen
    1.48
    𝘆
    1.46
    timeLeft
    1.42
     ruptured
    1.42
     stints
    1.41
    speople
    1.40
    жды
    1.39
    POSITIVE LOGITS
    l
    1.75
    st
    1.65
    lah
    1.55
    stion
    1.50
    r
    1.40
    lm
    1.38
    azione
    1.38
    nement
    1.36
    lard
    1.35
    ด์
    1.33
    Activations Density 0.012%

    No Known Activations