© 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. 22-GEMMASCOPE-2-RES-262K
    7. 5221
    Prev
    Next
    INDEX
    Explanations

    concepts ending in ism or special characters

    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_22_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
    est
    1.09
     despe
    1.02
    acre
    1.02
    
    0.97
    ad
    0.97
    s
    0.97
    𝚖
    0.96
    el
    0.96
    最好
    0.93
     Certainly
    0.92
    POSITIVE LOGITS
    zta
    1.18
     θεω
    1.17
     basiert
    1.15
     نج
    1.14
     أنها
    1.14
    újo
    1.13
     أنه
    1.11
    ណៈ
    1.09
     nécessaires
    1.08
    спользова
    1.06
    Activations Density 0.000%

    No Known Activations