© 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. 98137
    Prev
    Next
    INDEX
    Explanations

    own possessions

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

    attacker gains access

    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
    ig
    0.45
     organizers
    0.44
     operators
    0.43
    م
    0.39
    となる
    0.38
    scopes
    0.38
    Ξ
    0.38
    沪
    0.38
    apps
    0.38
    ថ្
    0.38
    POSITIVE LOGITS
     seinem
    0.59
     தனது
    0.50
     Selbst
    0.48
     своему
    0.46
     తన
    0.45
     પોતાની
    0.45
     partenaire
    0.45
     आत्म
    0.45
     swojego
    0.44
     героя
    0.44
    Activations Density 0.002%

    No Known Activations