© 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. 134643
    Prev
    Next
    INDEX
    Explanations

    location information and questions

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

    ethics, morals, household staff

    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
     K
    0.50
     MAS
    0.49
     stricken
    0.47
     Marvel
    0.46
     H
    0.46
     JOUR
    0.45
     TV
    0.45
     W
    0.44
     j
    0.44
     PVC
    0.44
    POSITIVE LOGITS
    nosi
    0.54
    𝙨
    0.52
    euros
    0.50
    isjon
    0.50
    🈵
    0.50
    ეგისტრ
    0.50
    elik
    0.49
    𒉰
    0.48
    elim
    0.47
    尔多
    0.47
    Activations Density 0.000%

    No Known Activations