© 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. 219540
    Prev
    Next
    INDEX
    Explanations

    social hierarchy or negative states

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

    fees, comparable, included

    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
     CED
    0.56
     cDNA
    0.52
    де
    0.51
    О
    0.50
     CYP
    0.48
     MED
    0.47
    Med
    0.46
    מ
    0.46
    গ
    0.46
     LUX
    0.46
    POSITIVE LOGITS
     persecution
    0.49
    EnglishMarks
    0.46
     imprison
    0.46
     aristocracy
    0.46
    arthritis
    0.44
     selfish
    0.43
    leyball
    0.43
     militant
    0.43
     feudal
    0.42
     resentment
    0.42
    Activations Density 0.000%

    No Known Activations