© 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. 125637
    Prev
    Next
    INDEX
    Explanations

    if and then

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

    foreign language or programming context

    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
    ِن
    0.48
    subsec
    0.48
    uj
    0.47
    㑯
    0.46
    zocht
    0.46
    sburg
    0.46
    successful
    0.45
    lii
    0.45
     सफलतापूर्वक
    0.45
    位
    0.45
    POSITIVE LOGITS
     ⇒
    0.46
     français
    0.44
     altru
    0.43
    ﺑ
    0.43
     matrim
    0.43
     ويم
    0.43
     francés
    0.42
     differentiation
    0.42
     française
    0.41
     eğer
    0.41
    Activations Density 0.001%

    No Known Activations