© 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. 68
    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
     వివర
    0.77
     необы
    0.76
    悩
    0.73
    ewöhn
    0.73
     razlik
    0.70
     വ്യത്യ
    0.69
    ాలంటే
    0.69
    冋
    0.67
    Noeud
    0.67
    frameNStart
    0.66
    POSITIVE LOGITS
     propagand
    1.86
     propaganda
    1.77
     obfusc
    1.58
     pretending
    1.56
     disinformation
    1.53
     pretends
    1.51
     falsely
    1.50
     parro
    1.50
     rhetoric
    1.50
     arrog
    1.43
    Activations Density 3.794%

    No Known Activations