© 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. 194519
    Prev
    Next
    INDEX
    Explanations

    science and academic terms

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

    propagating ideology or specific concepts

    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
    er
    0.59
    ли
    0.53
     bane
    0.49
    erat
    0.49
    teri
    0.49
    లు
    0.47
    扑
    0.47
    :|
    0.46
    uni
    0.46
    une
    0.45
    POSITIVE LOGITS
     étudier
    0.57
     Ciencias
    0.54
     adherents
    0.50
     médicos
    0.49
     Ciências
    0.48
     accompagnée
    0.48
    АС
    0.47
     INVEST
    0.47
     Scienze
    0.47
     egli
    0.46
    Activations Density 0.003%

    No Known Activations