© 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. 157618
    Prev
    Next
    INDEX
    Explanations

    responsibility or liability

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

    health or treatment

    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
    /
    0.51
     if
    0.50
     Basis
    0.50
     حتى
    0.43
     Alford
    0.43
     Depending
    0.42
     אם
    0.41
    ier
    0.41
     depending
    0.41
     Somebody
    0.41
    POSITIVE LOGITS
     nejen
    0.48
     useNavigate
    0.46
    Ｈ
    0.44
    ্যাং
    0.44
    不仅
    0.43
     sabía
    0.43
     frère
    0.43
    ﺍ
    0.42
    ᴄ
    0.42
     hög
    0.41
    Activations Density 0.011%

    No Known Activations