© 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. 184468
    Prev
    Next
    INDEX
    Explanations

    manufacturing, cleaning, costs, industry

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

    protecting from harm

    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
     எல்லா
    0.46
     miguel
    0.46
     टाइ
    0.45
     إلى
    0.43
     બહાર
    0.42
    Angelo
    0.41
    🌩
    0.41
    cardo
    0.41
    ستين
    0.41
     ذلك
    0.41
    POSITIVE LOGITS
     custodians
    0.51
     prosecution
    0.50
     replicas
    0.49
     tactics
    0.47
     grips
    0.47
     functionals
    0.47
    RIER
    0.47
     dilutions
    0.47
     suspension
    0.46
    媇
    0.46
    Activations Density 0.000%

    No Known Activations