© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 3431
    Prev
    Next
    INDEX
    Explanations

    SAMHSA National Helpline

    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_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    icae
    0.88
    cipit
    0.80
    ებმა
    0.77
    
    0.73
     JUN
    0.73
    ضة
    0.71
    นิด
    0.71
    Decorator
    0.71
    incer
    0.70
    ❸
    0.69
    POSITIVE LOGITS
     शव
    0.86
     overwhelming
    0.75
     invoking
    0.74
     तबाद
    0.72
     każde
    0.65
     dank
    0.65
     typesetting
    0.64
     freeing
    0.64
     imposition
    0.64
     encompassing
    0.64
    Activations Density 0.018%

    No Known Activations