© 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. 161380
    Prev
    Next
    INDEX
    Explanations

    funeral services, required, Heaven, yards, Events, mile

    np_acts-logits-general · gemini-2.5-flash-lite

    calculating rate and variation

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    da
    0.62
    s
    0.59
    ko
    0.57
    ton
    0.56
    ens
    0.54
    k
    0.54
    um
    0.52
    ink
    0.51
    örm
    0.50
    ark
    0.49
    POSITIVE LOGITS
     tří
    0.51
     restitu
    0.51
    الوج
    0.50
     mecan
    0.50
    త్మిక
    0.50
     mécanismes
    0.49
     calcul
    0.48
    المل
    0.48
    。
    0.48
     cherche
    0.48
    Activations Density 0.000%

    No Known Activations