© 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. 23763
    Prev
    Next
    INDEX
    Explanations

    Encyclopædia Britannica entries

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

    Britannica links

    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
     tutaj
    0.54
     impactos
    0.53
     Github
    0.51
    郋
    0.50
    备注
    0.50
    baixo
    0.47
     Vocês
    0.47
     girly
    0.46
    炁
    0.46
     vocês
    0.46
    POSITIVE LOGITS
     Encyclopædia
    0.65
     chiefly
    0.64
    Encycl
    0.61
     schoolchildren
    0.61
    britann
    0.59
     firsthand
    0.57
     Britannica
    0.55
     postwar
    0.49
     semia
    0.49
    qv
    0.48
    Activations Density 0.030%

    No Known Activations