© 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. 47770
    Prev
    Next
    INDEX
    Explanations

    because or can in multiple languages

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

    reason or capability

    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
    5
    0.57
    4
    0.52
    unfair
    0.43
    ?
    0.42
    積み
    0.41
    ة
    0.40
    atients
    0.40
    uny
    0.40
    1
    0.40
    6
    0.39
    POSITIVE LOGITS
     можно
    0.55
     ಏಕೆಂದರೆ
    0.55
     چون
    0.54
     puisque
    0.52
     çünkü
    0.52
     deoarece
    0.51
     perché
    0.51
     można
    0.50
     можна
    0.50
     வெறு
    0.50
    Activations Density 0.000%

    No Known Activations