© 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. 5055
    Prev
    Next
    INDEX
    Explanations

    Defaults to value

    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
     distinguishes
    0.73
    .​​
    0.71
    .
    0.68
    .​
    0.67
    oft
    0.67
     dissimilar
    0.66
     distinguish
    0.66
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.65
    inguish
    0.65
    good
    0.65
    POSITIVE LOGITS
     recoge
    0.79
     construire
    0.77
     restent
    0.76
     есть
    0.75
     ނ
    0.75
     enterr
    0.75
     cidade
    0.74
     inexist
    0.74
     повре
    0.73
     Movements
    0.73
    Activations Density 0.018%

    No Known Activations