© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 808
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ilgan
    0.71
    afety
    0.66
     ప్రమా
    0.66
     Burgess
    0.66
     Nakamura
    0.63
     वेर
    0.63
    acés
    0.63
    깅
    0.61
    itoa
    0.60
    agaman
    0.59
    POSITIVE LOGITS
     minds
    3.91
     mind
    3.88
     hearts
    3.33
    mind
    3.30
     Mind
    3.18
     MIND
    3.11
    Mind
    3.10
     Minds
    3.09
     heart
    2.96
     psyche
    2.88
    Activations Density 1.125%

    No Known Activations