© 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. 135773
    Prev
    Next
    INDEX
    Explanations

    for a

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

    societal bias and cultural norms

    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
     BM
    0.47
     ISD
    0.43
     markets
    0.43
     B
    0.42
     via
    0.41
     Department
    0.40
     RIA
    0.40
     منف
    0.40
    ukone
    0.40
     Via
    0.39
    POSITIVE LOGITS
    ্লীল
    0.46
    狙
    0.45
    وی
    0.43
     која
    0.42
    أ
    0.41
     malignant
    0.41
    やま
    0.41
     descenso
    0.41
    aecat
    0.41
     якая
    0.41
    Activations Density 0.004%

    No Known Activations