© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 193200
    Prev
    Next
    INDEX
    Explanations

    passive income and aggression

    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_40_width_262k_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
     active
    0.45
    anyang
    0.41
    active
    0.39
    ré
    0.39
    esto
    0.39
     Quỳnh
    0.38
     É
    0.38
    toto
    0.37
    呈
    0.37
     Tong
    0.37
    POSITIVE LOGITS
     passive
    0.63
     passively
    0.63
     Passive
    0.61
    Passive
    0.59
     aggressive
    0.59
     aggressiveness
    0.58
     agres
    0.55
     aggressively
    0.53
    passive
    0.53
     агре
    0.51
    Activations Density 0.005%

    No Known Activations