© 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. 258181
    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
     erstes
    0.49
     সর্বপ্রথম
    0.49
    ਪ
    0.47
    法施行令
    0.46
    owane
    0.45
    aites
    0.45
     Applying
    0.44
     Excited
    0.44
     Voters
    0.44
    ぴ
    0.44
    POSITIVE LOGITS
     hide
    0.51
     cant
    0.50
    DisplayText
    0.46
     consumable
    0.46
     brownie
    0.46
    会話
    0.45
     creeping
    0.45
    샤
    0.45
    링크
    0.44
     honed
    0.44
    Activations Density 0.000%

    No Known Activations