© 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. 54346
    Prev
    Next
    INDEX
    Explanations

    error, same, Mid, The, aquarium, well, heat, value, Marijuana, carbon

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

    critical especially several

    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
    ไข
    0.52
    )。
    0.48
    )，
    0.47
    𝐳
    0.46
     ไข
    0.46
    没错
    0.45
    的時候
    0.44
    єю
    0.44
    )،
    0.44
    詹
    0.44
    POSITIVE LOGITS
     amput
    0.57
     disgraced
    0.55
     actively
    0.55
     viaj
    0.53
     image
    0.51
     travel
    0.51
     assessing
    0.51
     opera
    0.50
     assesses
    0.50
     insurance
    0.50
    Activations Density 0.000%

    No Known Activations