© 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. 161872
    Prev
    Next
    INDEX
    Explanations

    sporting events, auctions, or mining operations

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

    financial responsibility managing intimate moments

    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
    њу
    0.52
    Latency
    0.49
    Displays
    0.48
    Embedded
    0.48
    ]={"
    0.48
    表示
    0.48
    成分
    0.47
    𝚖
    0.47
    を見た
    0.46
    Vine
    0.46
    POSITIVE LOGITS
     wzrost
    0.49
     renda
    0.47
     uang
    0.46
     Treasury
    0.45
     Myanmar
    0.45
     laboratorio
    0.44
     kimia
    0.43
     filtra
    0.43
     ninth
    0.43
     dialogo
    0.43
    Activations Density 0.000%

    No Known Activations