© 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. 22-GEMMASCOPE-2-RES-65K
    7. 5242
    Prev
    Next
    INDEX
    Explanations

    come up with

    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
     komma
    0.94
     attributed
    0.84
    sick
    0.84
    rystal
    0.83
    ੀ
    0.82
    sam
    0.82
    sony
    0.82
     misleading
    0.80
    衰
    0.80
    ია
    0.79
    POSITIVE LOGITS
    acken
    0.84
     har
    0.83
    នូវ
    0.81
    icile
    0.78
    меры
    0.77
    har
    0.77
    barung
    0.75
     élabor
    0.74
    ങ്
    0.74
    жа
    0.74
    Activations Density 0.019%

    No Known Activations