© 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. 224539
    Prev
    Next
    INDEX
    Explanations

    kinds of

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

    responsibility and accountability

    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
    ла
    0.55
    م
    0.51
    м
    0.48
    在家
    0.47
     orchids
    0.46
    迫
    0.46
    瀾
    0.46
    жа
    0.46
    家
    0.45
    啓
    0.45
    POSITIVE LOGITS
     Dividend
    0.50
     genere
    0.50
     Canc
    0.47
    azioni
    0.46
    kV
    0.46
     Introduce
    0.46
     welchem
    0.45
     det
    0.44
     Shareholders
    0.44
    잍
    0.44
    Activations Density 0.000%

    No Known Activations