© 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. 6944
    Prev
    Next
    INDEX
    Explanations

    encouraging groups of people

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

    informing or guiding people

    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
    (""))
    0.30
     idols
    0.28
     molybdenum
    0.27
     êtres
    0.26
     sigmoid
    0.26
     selectable
    0.25
     isos
    0.25
     ×
    0.25
     Aş
    0.25
    '
    0.25
    POSITIVE LOGITS
    人们
    0.46
     investors
    0.42
    人們
    0.41
     employers
    0.41
     people
    0.40
    大家
    0.38
     voters
    0.38
     viewers
    0.37
     लोगों
    0.37
     listeners
    0.35
    Activations Density 0.367%

    No Known Activations