© 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. 184112
    Prev
    Next
    INDEX
    Explanations

    buying insurance

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

    time travel scenarios and paradoxes

    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
     sponsored
    0.45
     dobra
    0.45
    sponsored
    0.44
     груп
    0.43
     société
    0.43
     غادي
    0.43
     җ
    0.42
     தேர்த
    0.42
     després
    0.42
     après
    0.42
    POSITIVE LOGITS
    粘
    0.46
    黏
    0.46
     Liquids
    0.44
     Inhibition
    0.43
    看出
    0.42
    丁目
    0.40
     aggravating
    0.40
     Obviously
    0.40
    明显
    0.40
    llabus
    0.40
    Activations Density 0.001%

    No Known Activations