© 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. 6258
    Prev
    Next
    INDEX
    Explanations

    religious offerings and priests

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

    who will inherit

    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
     பெரும்பாலும்
    0.56
    nashvillehousing
    0.55
    𐰇
    0.54
     могли
    0.53
     दोघा
    0.53
     турни
    0.52
     официа
    0.50
     கதாபா
    0.50
     பெரும்பாலான
    0.50
     கதாபாத்திர
    0.50
    POSITIVE LOGITS
     the
    0.54
     first
    0.51
     Chan
    0.50
     whose
    0.48
     Science
    0.48
     Praise
    0.48
     a
    0.47
     one
    0.47
     Son
    0.47
     let
    0.47
    Activations Density 0.032%

    No Known Activations