© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1519
    Prev
    Next
    INDEX
    Explanations

    obsession and possession

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ESTABL
    -0.79
    ختی
    -0.79
    PreExecute
    -0.77
     rebus
    -0.75
    "=>$
    -0.75
     chives
    -0.75
     Edits
    -0.74
     riso
    -0.74
     департа
    -0.73
     response
    -0.73
    POSITIVE LOGITS
    ession
    1.30
     Poss
    1.27
     possession
    1.14
     possess
    1.12
     posses
    1.05
    Poss
    1.02
    cession
    1.01
     possessions
    1.01
     possessed
    1.00
     possessor
    1.00
    Activations Density 0.029%

    No Known Activations