© 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
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-65K
    4. 1095
    Prev
    Next
    INDEX
    Explanations

    It’s

    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_65k_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
     Python
    0.59
     M
    0.58
     Z
    0.52
     Math
    0.49
     F
    0.49
     Java
    0.48
     Node
    0.48
     Am
    0.47
     C
    0.46
     Met
    0.46
    POSITIVE LOGITS
    zynarod
    0.73
    țiilor
    0.71
    ziehungen
    0.70
     produse
    0.68
     customarily
    0.67
     oftent
    0.66
    溂
    0.66
     теркәлүсез
    0.65
    <unused2130>
    0.65
     ብዙውን
    0.65
    Activations Density 3.278%

    No Known Activations