© 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. 1470
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    具有
    0.87
     specular
    0.87
     characterizing
    0.78
     विशेषताओं
    0.78
    继承
    0.77
     персона
    0.77
    寬
    0.77
    特征
    0.77
     especificar
    0.76
     érde
    0.74
    POSITIVE LOGITS
     hormones
    1.47
     metabolism
    1.37
     muscles
    1.35
     physiology
    1.31
     physiologically
    1.30
     neurotrans
    1.30
     cortisol
    1.30
     hormone
    1.27
     metabolismo
    1.27
     metabol
    1.25
    Activations Density 1.642%

    No Known Activations