© 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. 201299
    Prev
    Next
    INDEX
    Explanations

    contained/related/featured/found/anti/online/0/basis

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

    potential offense or discomfort

    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
     energético
    0.59
    龚
    0.48
     deporte
    0.45
     energet
    0.45
     énergétique
    0.44
    Format
    0.44
     домашних
    0.43
     মিন
    0.42
     deportiva
    0.41
     electrónico
    0.41
    POSITIVE LOGITS
    Chancellor
    0.51
     smugg
    0.50
    する場合
    0.50
     Chancellor
    0.49
    }$\
    0.48
    もしくは
    0.46
     または
    0.45
    ambu
    0.44
    }-
    0.44
     うん
    0.44
    Activations Density 0.000%

    No Known Activations