© 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. 259309
    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
    Peer
    0.46
     इनकी
    0.43
    ᵀ
    0.42
    lico
    0.41
    지
    0.41
    Imm
    0.41
    Resistance
    0.40
    ogenesis
    0.40
     dư
    0.40
    Players
    0.40
    POSITIVE LOGITS
     gute
    0.49
    弔
    0.48
     সমাজ
    0.47
     പൊതു
    0.47
     truce
    0.46
    私たちは
    0.46
    釣り
    0.45
    呀
    0.45
     renovated
    0.44
     Londra
    0.44
    Activations Density 0.001%

    No Known Activations