© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 254120
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     Reduce
    0.49
     Kindly
    0.47
     Attached
    0.47
    AvlTree
    0.45
    Reduce
    0.45
    第一个
    0.44
    呷
    0.44
    KR
    0.44
    ucci
    0.43
    ulli
    0.43
    POSITIVE LOGITS
     defense
    0.51
    granular
    0.49
    ς
    0.48
     sailboat
    0.48
     defesa
    0.47
     impenetrable
    0.47
     pénétr
    0.47
     defence
    0.47
     grassroots
    0.46
     arbor
    0.46
    Activations Density 0.001%

    No Known Activations