© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 54310
    Prev
    Next
    INDEX
    Explanations

    wealth concentration in a few

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     engineering
    0.44
    グリーン
    0.41
    疹
    0.38
    一旦
    0.37
     temporarily
    0.37
    maat
    0.36
     disciplines
    0.36
     substitutions
    0.36
     sofern
    0.36
     borrowed
    0.35
    POSITIVE LOGITS
     monopol
    0.63
     privileged
    0.59
     profite
    0.59
     olig
    0.56
     privilege
    0.55
     privilegio
    0.54
    垄
    0.54
    利益
    0.54
     monopoly
    0.53
     elites
    0.51
    Activations Density 0.076%

    No Known Activations