© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 1495
    Prev
    Next
    INDEX
    Explanations

    actions and outcomes

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ísica
    0.86
    igenza
    0.84
    注重
    0.79
    ocial
    0.78
    ご了承ください
    0.77
    uces
    0.76
    Normdaten
    0.76
    
    0.75
     आध्यात्म
    0.75
     spirituality
    0.75
    POSITIVE LOGITS
     efforts
    1.28
     Efforts
    1.11
     preparations
    1.06
     attempts
    1.02
     усилия
    0.97
     shipments
    0.93
     esforços
    0.89
     assertions
    0.89
     decisions
    0.88
     použití
    0.87
    Activations Density 0.525%

    No Known Activations