© 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. 35895
    Prev
    Next
    INDEX
    Explanations

    Man, Manu, manipulate, manufactured

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

    manipulation and undue influence

    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
    𝗺
    0.75
    ب
    0.72
    nies
    0.70
    nie
    0.68
    li
    0.67
    nin
    0.66
    mol
    0.66
    ethyl
    0.65
    nä
    0.64
    ms
    0.64
    POSITIVE LOGITS
     MAN
    0.72
     Manu
    0.71
     manipulator
    0.70
    ى
    0.70
     manipulate
    0.68
    מן
    0.64
     Man
    0.63
     manu
    0.62
     マン
    0.62
    يدة
    0.61
    Activations Density 0.058%

    No Known Activations